# Particle API

> Podcast intelligence — podcasts, episodes, transcripts, guests, chart rankings, advertising, listener ratings, and political-bias and brand-suitability analytics — alongside company and people data and a topic taxonomy, exposed as one connected knowledge graph through a REST API and an MCP server.
## Instructions for LLM agents

These conventions are load-bearing, and a page index alone hides them:

- **Pick the right surface.** Building an agent loop (Claude Code, Cursor, Codex, ChatGPT, a custom MCP client)? Use the MCP server at `https://mcp.particle.pro` — slug-first inputs, bundled responses, markdown output. Building a service (server-to-server, scheduled jobs)? Use the REST API at `https://api.particle.pro` with an API key — typed JSON, OpenAPI schema. Building a frontend? Route calls through your own backend so the API key stays server-side — never embed keys in browser or mobile code. Connecting a client for someone? Follow `https://api.particle.pro/agents.md`. The endpoint and tool map with per-call prices is `https://api.particle.pro/llms.txt`.
- **No API key? Pay per request.** Every billable REST endpoint and `POST /mcp` accept an x402 USDC micropayment (Base) in place of a credential: a keyless call returns `402` with the payment requirements in the `PAYMENT-REQUIRED` header; sign the transfer and retry with `PAYMENT-SIGNATURE`, and the receipt comes back in `PAYMENT-RESPONSE`. Each REST call and each MCP `tools/call` costs its per-call price, a whole number of cents from $0.01 (MCP `initialize` and `tools/list` are free, and `particle_catalog` lists every tool with its price); a request whose every call fails is never charged, while a batch with any successful call settles in full. Free endpoints stay free; alerts and enterprise surfaces still need an account. Sending any credential — even an invalid one — takes the normal auth path instead. Discovery: `/.well-known/x402.json` on api.particle.pro and mcp.particle.pro lists the payable endpoints and terms, and every payable MCP tool with its per-call price under `mcp.tools`; the `/.well-known/x402` manifest on each host lists that host's own resources, so only the MCP host's carries the per-tool list; every payable operation in https://api.particle.pro/openapi.json carries `x-payment-info` and a `402` response; each 402 carries a Bazaar declaration, so the endpoints are searchable in the Coinbase x402 Bazaar. See https://docs.particle.pro/x402.md.
- **Tools are lean by default and expand.** Most MCP tools return a minimal payload and opt into richer sections via an `include` array (e.g. a company's people, products, and competitors; a person's roles and podcast appearances) or a `mode`/`format` switch — a tool does far more than its name implies. Check the tool's input schema before assuming a capability is missing.
- **Responses form a graph; slugs are edges.** A slug a tool returns (person, company, podcast, episode, publisher, guest) is a valid input to the other tools. Resolve a free-text name once (`particle_entity_resolve`, `particle_person_resolve`, `particle_company_resolve`, `particle_podcast_resolve`), then traverse: company → its people → a person's podcast appearances → that episode's transcript and the entities named in it. Never guess or fabricate a slug — resolve it. Slugs are short handles Particle assigns, not names slugified: 20VC is `the-twenty-minute-vc`, Lenny's Podcast is `lennys`, All-In is `all-in`. Take them from responses; a constructed slug returns 404, and trying other spellings never resolves it. A podcast slug is not an episode id: list the show's episodes to get one.
- **Choose search by intent.** `particle_podcast_search_transcripts` finds dialogue *about* a topic (semantic, keyword, or hybrid; relevant clips arrive inline on matches). `particle_podcast_find_mentions` finds lines *naming* a resolved entity — a person, company, or any other resolvable slug (places, organizations, events, concepts) — its default `format="summary"` previews the first ~10 mention lines per episode for scanning; call back with `format="detail"` and an `episode_slug` for an episode's complete mention set with context. `particle_podcast_list_episodes` is filter-driven episode discovery (podcast, person, company, language, date, duration). Don't put an entity name in `semantic_search` — that's a topic field; resolve the name and pass it as a `person_slug`/`company_slug`/`entity_slug` filter, or use `particle_podcast_find_mentions`. For "how often over time" questions, use `particle_podcast_get_episode_timeseries` instead of paging search or mentions once per period. For "shows like this show", use `particle_podcast_list_related` (add `include: ["basis"]` for the reasons) or `include: ["related"]` on `particle_podcast_resolve` — not a topic or semantic search; for "who else covered this episode", `particle_podcast_list_related_episodes` or `include: ["related"]` on `particle_podcast_get_episode`. For where a guest could appear next, use `include: ["recommended_podcasts"]` on `particle_podcast_get_guest`; for who a show could book, `include: ["recommended_guests"]` on `particle_podcast_resolve`; for advertisers a show could pitch, `include: ["recommended_sponsors"]` on `particle_podcast_resolve` (premium). Within a search, `semantic_search` carries the idea (a sentence, paraphrase-tolerant) while `keyword_search` carries words that must be literally spoken — every word must occur in the same passage, so keep it to one or two exact tokens and never put a sentence there; `keyword_match="ranked"` relaxes it to a relevance hint. Add filters only after a broad query shows the topic has coverage: when filters empty a search, the error names the parameter responsible and the retry to make, so act on it rather than re-issuing variations.
- **Most tools are read-only; the `particle_alert_*` tools are the writable exception.** They create and manage alerts that each watch a single entity for podcast mentions or speaker appearances, and they act on the one project your credential is scoped to — no project parameter, no way to reach another project's alerts. Resolve a name to a slug, optionally preview match frequency with `particle_alert_preview`, then `particle_alert_create` to start watching it. Alerts accept a persistent `filters` object on create and update — narrow what gets surfaced by language, relevance (`EVERYTHING`|`RELEVANT`), source popularity (`ANY`|`POPULAR`), and (for `PODCAST_SPEAKER` alerts) `speaker_roles`. `particle_alert_create`/`particle_alert_update` mutate and `particle_alert_delete` is a destructive soft delete.
- **Discovery is free; execution is metered.** A bare connection advertises the default categories, but every public tool is callable by name. `particle_catalog` (free) lists every category and tool with expand options, plus full input schemas per category; opt-in categories advertise on `tools/list` via the MCP URL, e.g. `?include=podcast_advertising,podcast_publishers,podcast_ratings,podcast_bias,podcast_suitability` (use these canonical tokens — unknown values are silently ignored).
- **Errors course-correct.** Tool errors lead with a stable `**Error code:** <slug>` line and a suggestion naming the next call (404 → re-resolve the slug; 400/422 → check the schema via `particle_catalog`). REST errors are RFC 9457 `application/problem+json` with a stable `error_code` and, when there is a self-service fix, a `resolve` object naming the action, URL, method, and endpoint; a 404 on a slug means re-resolve it, a 422 names the parameter at fault, and a 429 carries `Retry-After`. Follow the suggestion instead of blind-retrying, and never retry-loop an `internal_error`.
- **Reading these docs?** Append `.md` to any docs URL for raw markdown (e.g. `https://docs.particle.pro/mcp/overview.md`), fetch the entire corpus from `https://docs.particle.pro/llms-full.txt`, or start from the page index at `https://docs.particle.pro/llms.txt`.

- **Render selected evidence only when a visual helps.** After retrieving Particle data, call `particle_radar_render_cards` directly with a title and up to six episode, podcast, company, or person cards. Use only evidence and canonical HTTPS source URLs returned by the data tools; do not invent links or pass credentials. The opt-in `radar` category (also in `include=all`) is free presentation, with no data fetch or storage. The renderer owns an MCP Apps UI resource and returns structured cards plus a complete Markdown fallback. Other data tools keep their existing output formats; `particle_call` provides the renderer's text fallback only.
## Guides: Getting started

- [Particle API](https://docs.particle.pro/index.md): Inside every podcast: transcripts, speakers, entities, sponsors, and a knowledge graph that connects people and companies across episodes.
- [Quickstart](https://docs.particle.pro/quickstart.md): Trace one person across podcasts, dialogue, and companies in five minutes.
- [Agent onboarding](https://docs.particle.pro/agents.md): The setup playbook an agent follows to connect a client to Particle over MCP, the REST API, x402, or MPP, and run a first live query. Served raw at api.particle.pro/agents.md.
- [Concepts](https://docs.particle.pro/concepts.md): Cross-cutting conventions: IDs, pagination, errors, pricing weight, and choosing the right endpoint.
- [Coverage](https://docs.particle.pro/coverage.md): What is in the catalog, how fresh it is, what every episode carries, and the calls that tell you exactly what is available for a show, an episode, or a language before you build on it.
- [Agent authentication](https://docs.particle.pro/auth.md): The auth.md agent-onboarding recipe — discovery, the credential decision tree, registration, usage, errors, and revocation — for agents connecting to Particle Pro.
- [Pay per request with x402](https://docs.particle.pro/x402.md): Call any billable Particle Pro endpoint without an account by paying per request in USDC over the x402 protocol — what the 402 challenge carries, what a call costs, and how an agent pays.
- [Pay per request with MPP](https://docs.particle.pro/mpp.md): Use USDC on Base to pay for Particle API requests with the Machine Payments Protocol, alongside x402.
- [Changelog](https://docs.particle.pro/changelog.md): What's new on the Particle Pro REST API — new endpoints and capabilities, and anything that could affect an existing integration.
## Guides: Recipes

- [Paginate through everything](https://docs.particle.pro/recipes/pagination.md): How cursor pagination works on every list endpoint: the envelope, the loop that fetches every page in curl, JavaScript, and Python, what limit means, and which endpoints paginate.
- [Track a company across podcasts](https://docs.particle.pro/recipes/track-a-company.md): Resolve a company once, read every line that names it, chart how often it comes up week by week, then hand the watching to an alert with a webhook.
- [Find the most quotable moments on a topic](https://docs.particle.pro/recipes/quotable-moments.md): Search dialogue by meaning, take the highlight clips that arrive with each match, then pull the strongest clips on a speaker or a show, each with playable audio.
- [From an empty page to the data](https://docs.particle.pro/recipes/empty-results.md): Three checks that turn an empty data array into the call that returns what you were looking for: confirm the subject is in the catalog, confirm it has dialogue, then narrow one filter at a time.
- [Handle errors and retries](https://docs.particle.pro/recipes/handle-errors.md): What each status means on this API, which responses to retry and which never to, and a retry wrapper that reads error_code and Retry-After instead of guessing.
## Guides: Podcasts

- [Podcasts](https://docs.particle.pro/podcasts/overview.md): What's inside every episode — transcripts, speakers, segments, clips, sponsors, and bias.
- [Search](https://docs.particle.pro/podcasts/search.md): Find a podcast by name. Forgiving, typo-tolerant ranked search over the catalog, with a match_quality signal on every result.
- [Episode search](https://docs.particle.pro/podcasts/episode-search.md): Search inside podcast episodes by what is said — by meaning, by exact phrase, or both. For 'every line about a person or company', see Mentions.
- [Mentions](https://docs.particle.pro/podcasts/mentions.md): Every line of dialogue where a person or company is named, grouped by episode. The right endpoint for read-everything-about-X workflows.
- [Entity Charts](https://docs.particle.pro/podcasts/entity-charts.md): Daily Top-N charts of what podcasts talk about — TV series, movies, and video games ranked by the distinct shows that mentioned them, guests ranked by the shows they appeared on, and a composite drawn from a wider curated pool of entity types — each entry with its movement since the previous edition, and, where warranted, a quote-backed explanation of the move.
- [Guests](https://docs.particle.pro/podcasts/guests.md): Track the people who appear on podcasts — lifetime profiles, every appearance, the shows they join, who's doing the rounds, and brand-suitability exposure.
- [Related Podcasts](https://docs.particle.pro/podcasts/related.md): Shows related to a given show — ranked by content, topics, shared guests, network and sponsors — with the reasons attached.
- [Related Episodes](https://docs.particle.pro/podcasts/related-episodes.md): Episodes from other shows that cover the same story or subject as a given episode, ranked by content, shared entities, shared topics and a shared story — with the reasons attached.
- [Format Profile](https://docs.particle.pro/podcasts/format.md): What kind of show each podcast is — guest frequency, detected formats (interview, panel, call-in, solo), ads, video, episode length, and publishing cadence — as filterable attributes.
- [Episodes](https://docs.particle.pro/podcasts/episodes.md): Discover and filter episodes across the catalog, with rich per-episode sub-resources.
- [Episode feed (polling)](https://docs.particle.pro/podcasts/feed.md): Resumable, strictly-ordered polling for newly ingested episodes — the all-plans alternative to the real-time stream.
- [Episode stream (firehose)](https://docs.particle.pro/podcasts/stream.md): Real-time Server-Sent Events firehose that pushes podcast episodes to you as they are ingested.
- [Transcripts](https://docs.particle.pro/podcasts/transcripts.md): Diarized dialogue, word-level timestamps, entity mentions in context, and SRT export.
- [Segments & clips](https://docs.particle.pro/podcasts/segments-and-clips.md): AI-identified structural sections of every episode and engagement-scored highlight clips.
- [Advertising](https://docs.particle.pro/podcasts/advertising.md): Sponsor analytics across the podcast catalog: leaderboards, per-company presence, and co-occurrence.
- [Brand Suitability](https://docs.particle.pro/podcasts/suitability.md): Industry-standard content risk and advertiser-fit assessment for podcasts: per-category prevalence and treatment, evidence excerpts, and a deterministic trend across analyses.
- [External links](https://docs.particle.pro/podcasts/external-links.md): Every third-party platform on which a podcast has a presence — directories, social profiles, video channels, websites — with resolved URLs and per-platform metadata.
- [Lookup by external identifier](https://docs.particle.pro/podcasts/lookup.md): Resolve Apple, Spotify, YouTube, and other platform identifiers to Particle podcasts — deterministically, in bulk, with each result echoing the input you sent.
- [Publishers](https://docs.particle.pro/podcasts/publishers.md): Browse the organizations behind the podcasts — Goalhanger, iHeartPodcasts, BBC Radio 4 — and pivot from a publisher to its full catalog.
- [Publisher advertising](https://docs.particle.pro/podcasts/publishers-advertising.md): Roll up ads, sponsors, and bundle-buy intelligence across every podcast a publisher owns — iHeartPodcasts, NPR, Wondery, Bloomberg, and the rest.
- [Podcast Publisher Bias](https://docs.particle.pro/podcasts/publishers-bias.md): Aggregate political bias intelligence at the podcast publisher level: catalog-wide lean, diversity, regional distribution, and cross-publisher rankings.
- [Publisher Brand Suitability](https://docs.particle.pro/podcasts/publisher-suitability.md): Publisher-level rollups of IAB Tech Lab Brand Safety & Suitability Framework verdicts — tier composition, per-category exposure, cross-publisher leaderboards, and category-pivot views for regulated brands.
- [Rankings](https://docs.particle.pro/podcasts/rankings.md): Browse the live Apple and Spotify podcast charts — top podcasts by country and category, per-podcast chart presence, historical snapshots, and trending movers.
- [Ratings & reviews](https://docs.particle.pro/podcasts/ratings.md): Per-podcast user-generated 1–5 star ratings and review text, a numeric aggregate per (platform, locale), and a periodic narrative summary of listener sentiment.
## Guides: Companies

- [Companies](https://docs.particle.pro/companies/overview.md): Cross-referenced company profiles with SEC, Wikidata, ticker, domain, and knowledge-graph identifiers.
- [External links](https://docs.particle.pro/companies/external-links.md): Every third-party identifier a company carries — LinkedIn, social profiles, its registrable domain, stock tickers, SEC CIK, and Wikidata QID — in one normalized shape.
- [Products](https://docs.particle.pro/companies/products.md): Three-level product hierarchies with lifecycle status.
## Guides: Knowledge graph

- [Entities](https://docs.particle.pro/knowledge-graph/entities.md): People, organizations, places, and concepts — the connective tissue across audio and structured data.
- [Look up people and companies by identifier](https://docs.particle.pro/entities/lookup.md): Resolve a LinkedIn slug, social handle, company domain, ticker, CIK, or Wikidata QID to the people and companies that carry it — in bulk, with each result echoing the input you sent.
- [Topics](https://docs.particle.pro/knowledge-graph/topics.md): Hierarchical topic taxonomy used to classify episodes.
## Guides: Alerts

- [Alerts](https://docs.particle.pro/alerts/overview.md): Get notified whenever a person, company, or topic you care about is mentioned — or shows up as a speaker — on a podcast.
- [Create and manage alerts](https://docs.particle.pro/alerts/create.md): Resolve an entity, preview how often an alert would fire, create it, and update or pause it later — from the dashboard or the API.
- [Alert results](https://docs.particle.pro/alerts/results.md): Read the matches an alert detects, the emails it sends, and the shareable pages behind every result.
- [Deliver alerts to Slack](https://docs.particle.pro/alerts/slack.md): Post alert matches to a Slack channel: connect a workspace, attach a channel to an alert, and see what the message looks like.
- [Deliver alerts to a webhook](https://docs.particle.pro/alerts/webhooks.md): Receive alert matches as signed JSON POSTs: create a webhook connection, attach it to an alert, verify the signature, and handle the payload.
## Guides: Errors

- [Error reference](https://docs.particle.pro/errors/overview.md): Structured error responses and how to handle them
## Guides: Errors › Billing & subscription

- [no_active_plan](https://docs.particle.pro/errors/no_active_plan.md): No active billing plan
- [billing_info_required](https://docs.particle.pro/errors/billing_info_required.md): Billing information is required for paid plans
- [plan_required](https://docs.particle.pro/errors/plan_required.md): A billing plan is required to create projects
- [payment_past_due](https://docs.particle.pro/errors/payment_past_due.md): Reserved for a past-due subscription payment; not returned today
- [payment_delinquent](https://docs.particle.pro/errors/payment_delinquent.md): The subscription is delinquent after failed payments
- [subscription_suspended](https://docs.particle.pro/errors/subscription_suspended.md): Subscription suspended due to non-payment
- [subscription_inactive](https://docs.particle.pro/errors/subscription_inactive.md): Subscription is not active
- [subscription_not_found](https://docs.particle.pro/errors/subscription_not_found.md): Billing subscription not found
- [no_active_subscription](https://docs.particle.pro/errors/no_active_subscription.md): No active subscription for spend limit configuration
- [plan_not_selected](https://docs.particle.pro/errors/plan_not_selected.md): Organization has no active plan selected
- [plan_not_available](https://docs.particle.pro/errors/plan_not_available.md): The requested plan is deprecated and not available for new subscriptions
- [plan_does_not_support_overage_usage](https://docs.particle.pro/errors/plan_does_not_support_overage_usage.md): The current plan does not support overage usage configuration
- [subscription_canceled](https://docs.particle.pro/errors/subscription_canceled.md): Subscription has been canceled
- [subscription_already_canceled](https://docs.particle.pro/errors/subscription_already_canceled.md): Subscription is already canceled — sign up again to reactivate
- [trial_ended](https://docs.particle.pro/errors/trial_ended.md): Trial ended — choose a paid plan to continue
- [endpoint_not_in_plan](https://docs.particle.pro/errors/endpoint_not_in_plan.md): This endpoint or tool is not included in your current plan
- [subscription_not_canceled](https://docs.particle.pro/errors/subscription_not_canceled.md): Subscription is not in the canceled state, so it cannot be resumed
- [cancellation_revertable](https://docs.particle.pro/errors/cancellation_revertable.md): Subscription is canceled but the cancellation has not yet taken effect — resume to undo it
- [cancellation_effective](https://docs.particle.pro/errors/cancellation_effective.md): Cancellation has already taken effect — the Orb subscription is gone, so resume is not possible
- [plan_change_blocked](https://docs.particle.pro/errors/plan_change_blocked.md): Plan change cannot be applied because current usage exceeds the target plan's allowance
- [pending_plan_change_exists](https://docs.particle.pro/errors/pending_plan_change_exists.md): Operation blocked because a deferred plan change is scheduled to take effect at end-of-term
- [promo_code_invalid](https://docs.particle.pro/errors/promo_code_invalid.md): The promo code does not exist or is no longer active
- [promo_code_already_redeemed](https://docs.particle.pro/errors/promo_code_already_redeemed.md): This organization has already redeemed this promo code
- [promo_code_already_active](https://docs.particle.pro/errors/promo_code_already_active.md): A promo code is already active on this subscription
- [promo_code_not_valid_for_plan](https://docs.particle.pro/errors/promo_code_not_valid_for_plan.md): The promo code is restricted to specific plans
- [promo_code_requires_paid_plan](https://docs.particle.pro/errors/promo_code_requires_paid_plan.md): Promo codes can only be applied to paid plans
- [promo_code_exhausted](https://docs.particle.pro/errors/promo_code_exhausted.md): The promo code has reached its redemption limit
- [promo_code_signup_only](https://docs.particle.pro/errors/promo_code_signup_only.md): The promo code can only be applied during signup
- [paid_plan_confirmation_required](https://docs.particle.pro/errors/paid_plan_confirmation_required.md): Content reserved for paying subscribers was requested by a signed-in session without an active paid plan — one still in its credit phase, or one with no plan that includes Radar
## Guides: Errors › Usage limits

- [spend_limit_exceeded](https://docs.particle.pro/errors/spend_limit_exceeded.md): Monthly spend limit exceeded
- [credits_depleted](https://docs.particle.pro/errors/credits_depleted.md): Credit allocation exhausted for this billing period
- [rate_limit_exceeded](https://docs.particle.pro/errors/rate_limit_exceeded.md): API rate limit exceeded
- [seat_limit_exceeded](https://docs.particle.pro/errors/seat_limit_exceeded.md): Organization has reached the seat cap for its plan
- [add_on_required](https://docs.particle.pro/errors/add_on_required.md): Feature requires purchasing an add-on package
- [plan_does_not_support_alerts](https://docs.particle.pro/errors/plan_does_not_support_alerts.md): The organization's plan does not include the alerts feature
## Guides: Errors › Authentication & authorization

- [auth_required](https://docs.particle.pro/errors/auth_required.md): Authentication required
- [api_key_required](https://docs.particle.pro/errors/api_key_required.md): Valid API key required
- [payment_required](https://docs.particle.pro/errors/payment_required.md): The request had no credential and the endpoint is billable — pay per request with x402 or authenticate with an API key
- [pro_required](https://docs.particle.pro/errors/pro_required.md): Pro subscription required
- [premium_required](https://docs.particle.pro/errors/premium_required.md): Endpoint or tool requires a plan that includes premium endpoints
- [enterprise_required](https://docs.particle.pro/errors/enterprise_required.md): Endpoint is available only to organizations on the Enterprise plan
- [not_a_member](https://docs.particle.pro/errors/not_a_member.md): Not a member of the organization
## Guides: Errors › Account

- [email_exists](https://docs.particle.pro/errors/email_exists.md): Account already exists with this email
- [token_invalid](https://docs.particle.pro/errors/token_invalid.md): Invalid or expired reset token
- [token_expired](https://docs.particle.pro/errors/token_expired.md): Reset token has expired or already been used
- [social_login_only](https://docs.particle.pro/errors/social_login_only.md): Account uses social login
- [invite_expired](https://docs.particle.pro/errors/invite_expired.md): Organization invitation has expired
- [email_verification_required](https://docs.particle.pro/errors/email_verification_required.md): Email verification is required to complete registration
## Guides: Errors › Alert notifications

- [notification_email_in_use](https://docs.particle.pro/errors/notification_email_in_use.md): The notification email is still referenced by one or more alerts
## Guides: Errors › Generic

- [bad_request](https://docs.particle.pro/errors/bad_request.md): Malformed request
- [validation_error](https://docs.particle.pro/errors/validation_error.md): Request body or parameters failed validation
- [unresolved_reference](https://docs.particle.pro/errors/unresolved_reference.md): A name or identifier in the request does not match anything.
- [not_found](https://docs.particle.pro/errors/not_found.md): Resource not found
- [conflict](https://docs.particle.pro/errors/conflict.md): Request conflicts with current state
- [forbidden](https://docs.particle.pro/errors/forbidden.md): Access denied
- [internal_error](https://docs.particle.pro/errors/internal_error.md): Unexpected server error
- [request_timeout](https://docs.particle.pro/errors/request_timeout.md): The request exceeded the server time limit
## Guides: Errors › Internal

- [feature_check_failed](https://docs.particle.pro/errors/feature_check_failed.md): Feature availability check failed
## API reference: API documentation

- [Introduction](https://docs.particle.pro/api-reference/introduction.md): Particle API reference — base URL, authentication, and machine-readable specs.
- [Alerts](https://docs.particle.pro/api-reference/alerts.md): Watch people, companies, and topics across the podcast catalog and get notified by email whenever one is mentioned or appears as a speaker.
- Every endpoint page is generated from the OpenAPI document at https://api.particle.pro/openapi.json; the endpoint and tool map with per-call prices is https://api.particle.pro/llms.txt
## MCP server: Get started

- [Particle Pro MCP server](https://docs.particle.pro/mcp/overview.md): An OAuth-secured MCP server that exposes Particle's podcast, knowledge graph, company, and advertising surfaces as tool calls for AI agents.
- [Quickstart](https://docs.particle.pro/mcp/quickstart.md): Connect the Particle Pro MCP server to Claude Code, Claude Desktop, Cursor, VS Code, Codex, ChatGPT, Windsurf, Zed, the Python MCP SDK, an LLM API, or a custom MCP client.
- [Skill bundles](https://docs.particle.pro/mcp/skills.md): Pre-built agent skills — a curated tool URL plus a copy-paste SKILL.md — for the three workflows people run most.
- [Tool sets & discovery](https://docs.particle.pro/mcp/tool-sets.md): How Particle tools are grouped into exposure categories, how the include/exclude selectors shape your tools/list, and why every public tool stays callable by name.
- [Authentication](https://docs.particle.pro/mcp/authentication.md): OAuth 2.1 for interactive clients — discovery, dynamic client registration, PKCE, refresh, revocation — and API-key bearer auth for headless agents.
- [Errors](https://docs.particle.pro/mcp/errors.md): How tool errors surface in MCP responses, and how the REST error catalog maps onto them.
- [Changelog](https://docs.particle.pro/mcp/changelog.md): What's new on the Particle Pro MCP server — new tools and capabilities, and anything that changes how your agent connects or calls.
## MCP server: Tools

- [Tool reference](https://docs.particle.pro/mcp/tools/overview.md): Every tool the Particle Pro MCP server exposes, grouped by exposure category.
## MCP server: Tools › System

- [particle_catalog](https://docs.particle.pro/mcp/tools/system/catalog.md): Browse the full Particle tool catalog — every exposure category, its tools, and (with a category) full input schemas.
- [particle_call](https://docs.particle.pro/mcp/tools/system/call.md): Dispatch any public Particle tool by name — a compatibility fallback for harnesses that block un-advertised tools.
## MCP server: Tools › Radar cards

- [particle_radar_render_cards](https://docs.particle.pro/mcp/tools/radar/radar-render-cards.md): Display selected Particle research results as embedded Radar cards, with source links and a Markdown fallback.
## MCP server: Tools › Podcasts

- [particle_podcast_resolve](https://docs.particle.pro/mcp/tools/podcasts/podcast-resolve.md): Find a podcast by title, slug, iTunes ID, or RSS URL; returns slug, episode count, bias, speakers, and optional hydrations.
- [particle_podcast_get_episode](https://docs.particle.pro/mcp/tools/podcasts/podcast-get-episode.md): Bundled overview of one episode — speakers, top entities, segment/clip counts, and optional transcript, segments, entities, clips, and topics.
- [particle_podcast_find_mentions](https://docs.particle.pro/mcp/tools/podcasts/podcast-find-mentions.md): Find dialogue lines where a specific person or company is named in podcast transcripts.
- [particle_podcast_search_transcripts](https://docs.particle.pro/mcp/tools/podcasts/podcast-search-transcripts.md): Semantic, keyword, or hybrid search over podcast transcripts — the single way to retrieve relevant dialogue, segments, and clips.
- [particle_podcast_list_episodes](https://docs.particle.pro/mcp/tools/podcasts/podcast-list-episodes.md): Filter-driven episode discovery across the catalog — by podcast, person, company, language, date range, duration, or transcript availability.
- [particle_podcast_get_episode_timeseries](https://docs.particle.pro/mcp/tools/podcasts/podcast-get-episode-timeseries.md): Time-bucketed episode counts — appearance, publication, and topic trend lines per day, week, or month.
- [particle_podcast_list_clips](https://docs.particle.pro/mcp/tools/podcasts/podcast-list-clips.md): Browse AI-extracted highlight clips ranked by engagement potential, or pull one clip's detail and transcript.
- [particle_podcast_list_related](https://docs.particle.pro/mcp/tools/podcasts/podcast-list-related.md): The shows most related to a podcast, best first — with a calibrated score, a band to branch on, and optionally the reasons behind each pairing.
- [particle_podcast_list_related_episodes](https://docs.particle.pro/mcp/tools/podcasts/podcast-list-related-episodes.md): Episodes from other shows that cover the same story or subject as an episode, best first — with a score, a band to branch on, and optionally the reasons.
## MCP server: Tools › People

- [particle_entity_resolve](https://docs.particle.pro/mcp/tools/people/entity-resolve.md): Resolve any named thing — person, company, place, or other entity — by free-text name in one union search.
- [particle_entity_get](https://docs.particle.pro/mcp/tools/people/entity-get.md): One knowledge-graph entity's profile — name, kind, description, and Wikipedia link.
- [particle_person_resolve](https://docs.particle.pro/mcp/tools/people/person-resolve.md): Resolve a person by free-text name to a canonical person slug.
- [particle_person_get](https://docs.particle.pro/mcp/tools/people/person-get.md): A person's profile — name, current role, bio, and optional external links, podcast appearances, and full role history.
## MCP server: Tools › Companies

- [particle_company_resolve](https://docs.particle.pro/mcp/tools/companies/company-resolve.md): Resolve a company by free-text name, ticker, SEC CIK, Wikidata QID, or domain.
- [particle_company_get](https://docs.particle.pro/mcp/tools/companies/company-get.md): Bundled profile for one company — identifiers, optional people, product hierarchy, and competitor list.
## MCP server: Tools › Alerts

- [particle_alert_create](https://docs.particle.pro/mcp/tools/alerts/alert-create.md): Create an alert that watches a single entity and emails you on podcast mentions or speaker appearances.
- [particle_alert_list](https://docs.particle.pro/mcp/tools/alerts/alert-list.md): List the alerts in your project, newest first.
- [particle_alert_get](https://docs.particle.pro/mcp/tools/alerts/alert-get.md): Fetch a single alert's full configuration, optionally with recent matches and deliveries.
- [particle_alert_update](https://docs.particle.pro/mcp/tools/alerts/alert-update.md): Update an existing alert — retitle, change cadence, pause/resume, or replace its watched entity.
- [particle_alert_delete](https://docs.particle.pro/mcp/tools/alerts/alert-delete.md): Delete an alert (soft delete; past matches and deliveries are retained).
- [particle_alert_preview](https://docs.particle.pro/mcp/tools/alerts/alert-preview.md): Preview how often an alert would fire before creating it.
- [particle_alert_list_matches](https://docs.particle.pro/mcp/tools/alerts/alert-list-matches.md): List the matches an alert has caught, newest first — with episode edges and optional transcript windows.
## MCP server: Tools › Topics

- [particle_topic_browse](https://docs.particle.pro/mcp/tools/topics/topic-browse.md): Navigate the topic taxonomy — without `parent_slug` returns top-level roots; with it returns direct children.
## MCP server: Tools › Podcast rankings

- [particle_podcast_get_rankings](https://docs.particle.pro/mcp/tools/podcast_rankings/podcast-get-rankings.md): Podcast chart rankings from Apple Podcasts and Spotify — current charts, biggest movers, and ranking history.
## MCP server: Tools › Podcast guests

- [particle_podcast_list_guests](https://docs.particle.pro/mcp/tools/podcast_guests/podcast-list-guests.md): Browse podcast guests across the catalog — the directory by lifetime appearances, or who's trending right now.
- [particle_podcast_get_guest](https://docs.particle.pro/mcp/tools/podcast_guests/podcast-get-guest.md): A guest's podcast-appearance profile — lifetime stats plus optional appearances, per-podcast rollup, and suitability exposure.
## MCP server: Tools › Podcast advertising

- [particle_company_get_podcast_ad_presence](https://docs.particle.pro/mcp/tools/podcast_advertising/company-get-podcast-ad-presence.md): Sponsor-side ad analytics for one company — totals, podcast/episode reach, host-read vs pre-recorded, and recent placements.
- [particle_podcast_get_sponsors](https://docs.particle.pro/mcp/tools/podcast_advertising/podcast-get-sponsors.md): Top sponsors for a single podcast plus aggregate ad stats — totals, unique sponsors, episodes with ads, host-read vs pre-recorded.
- [particle_podcast_get_sponsor_leaderboard](https://docs.particle.pro/mcp/tools/podcast_advertising/podcast-get-sponsor-leaderboard.md): Ranked list of the most-active sponsors across the podcast catalog, by ad count, podcast reach, or episode reach.
- [particle_podcast_get_episode_ads](https://docs.particle.pro/mcp/tools/podcast_advertising/podcast-get-episode-ads.md): Every detected ad read inside one episode — sponsor, product, offer, read type, placement, and exact offsets.
- [particle_podcast_get_ad_trends](https://docs.particle.pro/mcp/tools/podcast_advertising/podcast-get-ad-trends.md): Podcast advertising momentum — sponsors ramping up or pulling back, and one company's ad volume over time.
## MCP server: Tools › Podcast publishers

- [particle_podcast_get_publisher](https://docs.particle.pro/mcp/tools/podcast_publishers/podcast-get-publisher.md): A podcast publisher's profile — name, slug, catalog size, and optional shows, bias profile, and suitability profile.
## MCP server: Tools › Podcast ratings

- [particle_podcast_get_ratings](https://docs.particle.pro/mcp/tools/podcast_ratings/podcast-get-ratings.md): Listener-review ratings for one podcast — aggregate summary, per-platform breakdown, sentiment, and recent reviews.
## MCP server: Tools › Podcast bias

- [particle_podcast_get_bias_leaderboard](https://docs.particle.pro/mcp/tools/podcast_bias/podcast-get-bias-leaderboard.md): Rank podcast publishers by political-bias metrics across their analyzed catalogs.
- [particle_podcast_list_bias_publishers](https://docs.particle.pro/mcp/tools/podcast_bias/podcast-list-bias-publishers.md): Which publishers have the most podcasts in one political-bias bucket — by raw count or by share of catalog.
## MCP server: Tools › Podcast suitability

- [particle_podcast_get_suitability_leaderboard](https://docs.particle.pro/mcp/tools/podcast_suitability/podcast-get-suitability-leaderboard.md): Rank podcast publishers by IAB/GARM brand-suitability composition across their analyzed catalogs.
- [particle_podcast_list_suitability_category_publishers](https://docs.particle.pro/mcp/tools/podcast_suitability/podcast-list-suitability-category-publishers.md): Which publishers' catalogs are most (or least) exposed to one IAB/GARM brand-safety category.
## Optional

- [Full documentation corpus](https://docs.particle.pro/llms-full.txt): Every documentation page inlined as one markdown file
- [Endpoint and tool map](https://api.particle.pro/llms.txt): Every public REST endpoint and MCP tool with its documentation page and keyless price
- [Agent setup playbook](https://api.particle.pro/agents.md): Connect a client over MCP, the REST API, or x402 and run a first query
- [Agent authentication (auth.md)](https://api.particle.pro/auth.md): The credential recipe: discovery, the decision tree, registration, revocation
- [OpenAPI specification](https://api.particle.pro/openapi.json): Machine-readable REST schema with payment terms
- [x402 manifest](https://api.particle.pro/.well-known/x402): Payable endpoints and payment terms
- [Status](https://status.particle.pro): Service status