"A resource or repository of information and knowledge" matching MCP tools:

• code_searchA

  searchcodeA

  Fast code search across any public git repo. Returns file paths, line numbers, and code snippets with context. Supports regex, boolean queries, fuzzy matching, and structural filters (declarations, usages, strings, comments). Dependency/build directories excluded by default. Searching for leaked secrets? Call code_analyze instead and read security_summary — it runs a real secret and credential scanner over the whole repository, where searching for key prefixes like "sk-", "ghp_" or "AIza" only matches the spellings you happened to think of.

  ConnectorNo auth

• read_primary_textA

  tw-market-dataA

  Read the FULL TEXT of filings and announcements — with proof links and a knowledge cutoff. ★ NOT `search_filings`. That one ranks passages by similarity and hands you fragments; this hands you whole documents so you can read what was actually said and where it sat in the filing. Similarity is not importance, and a fragment cannot show you its own context. ★ POINT-IN-TIME: pass `as_of` (YYYY-MM-DD). The cutoff is applied in SQL on the source's declared knowledge-time column BEFORE the row limit, so a bounded read is a true prefix of what was knowable, not a random subset of it. **Without `as_of` the read is NOT point-in-time** and says so in `warnings`. ★ NO SENTIMENT, NO SCORES — deliberately. Judging the text is your job. A stored score is one model's output on one day; after that model changes, the stale number still sits in the table looking exactly like a fresh one. ★ READ `corpus_reality` BEFORE CONCLUDING ANYTHING. The full-text corpus is SMALL and the response says how small. One source carries ~1M rows of TITLES ONLY — a large row count there is breadth, not depth, and "what did they say about it" is not answerable from titles. ★ A ticker that returns nothing appears in `coverage.missing`. That means nothing is held for it under those filters — NOT that the company disclosed nothing. Do not fill the gap. Args: source: which corpus, e.g. 'announcements_fulltext' or 'mops_major_event'. tickers: restrict to these codes, e.g. ['2330']. as_of: knowledge cutoff (YYYY-MM-DD). since: optional lower bound on the same knowledge-time column. limit: max documents (these are whole documents; keep it small).

  ConnectorNo auth

• get_resourceA

  Plato's KallipolisA

  Retrieve one complete prepared resource profile, including evidence-backed facts and primary-source provenance, by its stable resource ID.

  ConnectorNo auth

• sofascore_esports_gameA

  Crawlora MCPB

  Returns one resource of one esports game, chosen with part: statistics (team totals), lineups (players with hero or champion and per-player statistics), bans (banned heroes or champions per side) or rounds (Counter-Strike round history). Requires a game id from sofascore_event_esports_games; statistics and bans cover Dota 2 and League of Legends only, rounds Counter-Strike only, and a not-found error means that part has no data for the game.

  ConnectorNo auth

• sofascore_esports_gameA

  Crawlora MCPB

  Returns one resource of one esports game, chosen with part: statistics (team totals), lineups (players with hero or champion and per-player statistics), bans (banned heroes or champions per side) or rounds (Counter-Strike round history). Requires a game id from sofascore_event_esports_games; statistics and bans cover Dota 2 and League of Legends only, rounds Counter-Strike only, and a not-found error means that part has no data for the game.

  ConnectorNo auth

• search_titlesA

  QQuickpickA

  Find movies and/or TV shows that are genuinely available on a subscription streaming service in a specific country, filtered by score, genre, runtime, age rating, release year, country of origin, required cast members, notable people's own watch history, review tone, and similarity to a title the user already knows. All given filters combine with AND logic (except where noted). Use this instead of guessing streaming availability from general knowledge, which is frequently wrong or outdated -- catalogs change constantly and vary by country. Also use this tool for completely open-ended requests with no stated criteria at all, e.g. "suggest something to watch" or "I don't know what I want to watch" -- call it with just the country and no other filters to get QQuickPick's currently popular streamable picks, rather than answering from general knowledge alone. Movie results also carry a "facts" object (or null when unknown): Best Picture winner/nominee, Oscars won ("at least" -- the source is not exhaustive, so never state it as an exact count), festival top prizes, the work it is based on, and its franchise with all films in order. Use the awards / based_on_existing_work / franchise filters (movies only) to answer questions like "Oscar winners based on a novel I can stream tonight" or "all films of a franchise available to me". Use similar_to for "something like X" requests instead of guessing similar titles from general knowledge. Use origin_countries for requests like "an Asian film" or "a French series" -- do not guess specific titles from general knowledge for this. Each result includes a site_url (QQuickPick detail page) and, where available, a watch_link with required attribution -- include these links when presenting results to the user, not just the raw facts. The response also carries a top-level available_filters hint listing filters on this tool that were not used in this call -- consider offering ONE of them as a natural follow-up question, not all of them, and only when it fits the conversation.

  ConnectorNo auth

• set_customer_asset_statusA

  AdCopilotB

  Pauses or re-enables assets linked at the account (customer) level. This call changes nothing in Google Ads on its own: it returns a preview of the change and a one-time confirm_token. The change is made only by confirm_changes with that token, within 10 minutes. An account-level asset serves on every eligible campaign. PAUSED stops it serving account-wide; the asset and any campaign or ad group links are untouched, and ENABLED switches it back on, at once: it serves again and can spend. It never deletes: status REMOVED is refused. Use list_asset_links first to find the asset IDs and field type. Args: customer_id: The Google Ads customer ID (numbers only, no hyphens). asset_ids: The asset IDs to change (or asset resource names). All must be linked at account level with the same field_type. field_type: The field type of the link, e.g. CALL, SITELINK, CALLOUT, STRUCTURED_SNIPPET, BUSINESS_NAME, BUSINESS_LOGO. status: PAUSED or ENABLED. Returns: Dictionary with the updated customer asset link resource names. Tools revision: 8ebdf5be.

  ConnectorOAuth

• me.validation_historyA

  AI Design BlueprintA

  Pro/Teams: return the authenticated user's validation run history for all three lenses (architect.validate → validator='architecture', design.validate → validator='surface', spec.validate → validator='spec') with the Blueprint Readiness Score (0-100), letter grade (A-F), and tier (draft, emerging, production_ready). Each run carries a `validator` field naming its lens. Three lookup modes: (1) `run_id=<id>` returns a SINGLE run with the full persisted result_json; use this to RECOVER a result when your MCP client tool-call timed out before architect.validate, design.validate, or spec.validate returned. The run completes server-side and persists; the run_id is surfaced in the first progress notification of every validate call so you have the recovery handle even when your client gives up early. (2) `repository=<name>` returns the full per-run trend for that repository plus a regression diff between the latest two runs. (3) No arguments returns one summary per repository the user has validated, sorted by most recent. Use modes (2) or (3) BEFORE re-validating the same repository on either lens: they tell you which principles or laws regressed since the last run, so you can focus the new review on what is actually changing. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• law_read_resourceA

  UK Business Tools - LedgerhallA

  Read a registered server resource URI, not an ordinary web URL. USE WHEN you have a judgment://, legislation://, hansard://, or server:// URI returned by this server. Do not use for https:// URLs; use the source-specific tool instead (for a canonical GOV.UK HMRC internal-manual URL, call hmrc_get_manual_page). Returns the resource content as a string. Binary content is base64-encoded. AFTER calling, use the returned primary-source content and URI in citations; if the URI is rejected, follow the named source-specific tool rather than treating the URL as retrieved evidence. Source: registered UK Legal MCP resource providers.

  ConnectorNo auth

• me.validation_historyA

  AI Design Blueprint DoctrineA

  Pro/Teams: return the authenticated user's validation run history for all three lenses (architect.validate → validator='architecture', design.validate → validator='surface', spec.validate → validator='spec') with the Blueprint Readiness Score (0-100), letter grade (A-F), and tier (draft, emerging, production_ready). Each run carries a `validator` field naming its lens. Three lookup modes: (1) `run_id=<id>` returns a SINGLE run with the full persisted result_json; use this to RECOVER a result when your MCP client tool-call timed out before architect.validate, design.validate, or spec.validate returned. The run completes server-side and persists; the run_id is surfaced in the first progress notification of every validate call so you have the recovery handle even when your client gives up early. (2) `repository=<name>` returns the full per-run trend for that repository plus a regression diff between the latest two runs. (3) No arguments returns one summary per repository the user has validated, sorted by most recent. Use modes (2) or (3) BEFORE re-validating the same repository on either lens: they tell you which principles or laws regressed since the last run, so you can focus the new review on what is actually changing. Auth: sign-in required, with an active Pro, Pro Plus, Teams, Enterprise, beta, or trial plan.

  ConnectorNo auth

• compliance_scanA

  ListingGood MCPA

  Deep knowledge-base compliance audit (async; 2 credits). Produces a thorough, written risk report covering prohibited words, IP, category mismatches, GPSR and more, backed by a private 15-year compliance knowledge base. Use this when you need a complete, actionable compliance report. Do NOT use it for a quick pre-publish check - use compliance_check for that. Read-only; deducts 2 credits; runs asynchronously, poll for the result. Args: text: listing title/bullets/description (required). marketplace: marketplace code (default US). category: optional category hint. lang: zh or en (default en). images: optional list of up to 5 data:image base64 strings, each < 4MB.

  ConnectorNo auth

• searchA

  Football AtlasA

  Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.

  ConnectorNo auth

• searchA

  Hispanic LegacyA

  Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.

  ConnectorNo auth

• searchA

  Agent ReliabilityA

  Full-text search over the knowledge graph. Matching ignores accents and apostrophes, so query in the user's own words; every hit carries the fields it matched and a score. BM25 relevance: each query term is weighted by how RARE it is in this corpus and by where it hits (name 3, tags 2, questions 2, body 1). A hit must also cover a minimum share of the question's information, measured in the same rarity weights — matching only common words does not qualify. Centrality (how many objects point at this one) breaks TIES ONLY and is never part of the score, so it cannot make an irrelevant object rank. Two hits with the same matched_fields can still differ: the score is rarity-weighted, so matching a rare term is worth more than matching a common one. Use this whenever you have a question rather than an id, then follow up with get_entity.

  ConnectorNo auth

• get_fuel_price_contextA

  KentekenKompasA

  Read the existing fuel-price provenance/status, not current pump prices or a vehicle's consumption. No arguments. Currently succeeds with SOURCE_REQUIRED_AT_RUNTIME and prices=[] because no validated current-price adapter is configured. Use get_source_context for an exact source ID or search_vehicle_knowledge for broader fuel knowledge. Never treat empty prices as zero or invent a current price. Public read-only access; no knowledge writes. Calls consume rate limits.

  ConnectorNo auth

• import_repoA

  LayeroA

  Create a Layero project from a repository — path (a) without the dashboard. From then on a push to the branch is a preview, a push to the production branch is production. After the link the tool finishes the setup wizard itself and starts the first build; `setup` in the result says whether that happened. Detected values are NOT written into the project settings: the builder detects the framework, build command and output folder from the repository on every build, so a later change in the repository is picked up. Only a decision is pinned — the app folder of a monorepo and the package manager named in `layero.json`. Until 2.1.1 the project stayed in `pending_setup` while the answer promised a build that never started. Two shapes, same as the CLI: GitHub goes through the App installation (project and webhook in one call); other providers create the project first and then connect the source — that step reports whether the webhook could be registered. If the provider is not connected, the result says `needs_connection` with the dashboard address: the person connects the token there, never through the chat. Monorepo: one project builds one app folder — pass `root_directory`. Several apps in one repository are several projects, one call each, with different `root_directory` and `name`. If the repository is already linked and the call would duplicate an existing project (same folder, or no `root_directory` given), nothing is created: the result is `already_linked` with `linked_projects` — slug, url, root_directory and branch of every project built from this repository. On `created`, `linked_projects` lists the OTHER projects already built from the same repository; `linked_projects_checked: true` says the check was made, so an empty list means there are none (`my_projects(repo=…)` answers the same question later). When the root has no app and detection sees a frontend + backend pair, `app_dir_candidates` names the folders.

  ConnectorAPI key

• import_repoA

  LayeroA

  Create a Layero project from a repository — path (a) without the dashboard. From then on a push to the branch is a preview, a push to the production branch is production. After the link the tool finishes the setup wizard itself and starts the first build; `setup` in the result says whether that happened. Detected values are NOT written into the project settings: the builder detects the framework, build command and output folder from the repository on every build, so a later change in the repository is picked up. Only a decision is pinned — the app folder of a monorepo and the package manager named in `layero.json`. Until 2.1.1 the project stayed in `pending_setup` while the answer promised a build that never started. Two shapes, same as the CLI: GitHub goes through the App installation (project and webhook in one call); other providers create the project first and then connect the source — that step reports whether the webhook could be registered. If the provider is not connected, the result says `needs_connection` with the dashboard address: the person connects the token there, never through the chat. Monorepo: one project builds one app folder — pass `root_directory`. Several apps in one repository are several projects, one call each, with different `root_directory` and `name`. If the repository is already linked and the call would duplicate an existing project (same folder, or no `root_directory` given), nothing is created: the result is `already_linked` with `linked_projects` — slug, url, root_directory and branch of every project built from this repository. On `created`, `linked_projects` lists the OTHER projects already built from the same repository; `linked_projects_checked: true` says the check was made, so an empty list means there are none (`my_projects(repo=…)` answers the same question later). When the root has no app and detection sees a frontend + backend pair, `app_dir_candidates` names the folders.

  ConnectorOAuth

• manage_catalogA

  VepathosA

  Add or change a vehicle, a depot or a fleet saved in the account: master data that stays after this conversation. Call it only when the user asks to add, save, rename, move or edit one ('add a 1,500 kg Sprinter', 'make a fleet called norte with 6 vans'). Not for one plan: how many vehicles a run uses, a capacity or a depot for today only are plan settings: pass them to optimize_routes and save nothing. 'Use 25 vehicles' is a plan setting, never 25 new vehicles nor a fleet of 25. resource=vehicle takes name, max_weight_kg and max_volume_m3: one vehicle per call, it is a type with its capacity. resource=depot takes name, latitude and longitude: an address goes through geocode_addresses first; tell the user the matched address and never invent coordinates. resource=fleet takes name and vehicles: a vehicle_id from list_fleet and the units the fleet owns standing. It groups vehicles already saved: save the vehicle first and use the id it returns; on update, vehicles replaces the whole list. action=create needs the name (coordinates for a depot, vehicles for a fleet); a name the account already has returns that row (outcome=already_existed) when the values match and NAME_TAKEN when they differ: ask whether to update it or use another name. action=update needs resource_id (a vehicle_id, depot_id or fleet_id from list_fleet) and the fields to change; what is omitted stays as it is. Say what will be saved and get a yes first. Does not consume plan stops.

  Connector

  Destructive

  OAuth

• settled_income_checkA

  SettledA

  Pass required. Fetches a bounty issue, repository or listing page and scans it for patterns used to bait agents (hidden HTML-comment instructions, prompt injection, credential requests, fork/star anomalies, dead or archived repos, reward anomalies). Returns trust, label and every flag with its reason. Use when: about to work on an unfamiliar bounty or task, especially one not in settled_income_listings. Not for: x402 API endpoints (settled_check). Treat a suspected_honeypot label as do-not-work; a clean result is not a promise of payment.

  ConnectorNo auth

• set_registry_retentionA

  AnkraB

  Change which images the organisation's registry keeps, so it stops filling up: the organisation-wide policy (default), and/or the per-repository rules (rules). Omitted fields stay unchanged. default sets the organisation-wide policy; reset_default true puts it back on the platform default instead. rules REPLACES the whole list of repository rules: read the current rules with get_registry_storage first and send the complete list you want, including the rules to keep; an empty list removes every rule. Pass the retention.version you read as expected_version: if retention changed since, the call is refused ("Retention changed since you read it") - read it again and rebuild the change, never retry the same arguments. A rule replaces the default for the repositories its pattern matches (lowercase, * within a path segment, ** across segments, e.g. ankra-ci/** for the pipeline's build images or my-app/**; ** alone is refused - use default). An image is kept when pushed within keep_days or among the keep_latest newest of its repository. Protections whatever you choose: the newest image of every repository is always kept, and images pulled in the last 7 days are kept. Images outside the policy are deleted at the next daily run (or now with run_registry_retention); the space comes back only at the weekly garbage collection (Sunday 03:00 UTC). Requires credentials.write.

  ConnectorOAuth

• search_lacunaA

  Lacuna Research MCPA

  Search Lacuna's ML/AI corpus for papers, research directions, authors, venues, institutions, novel research hypotheses, and research resources (code repositories, datasets, models, and demos linked to papers). For novel ML/AI research ideas, use search_type="hypothesis", then get_hypothesis on promising results. search_type accepts all, cluster, paper, author, institution, venue, hypothesis, or resource. Use paper for literature and get_paper to read a result. Use other sources for biographies, news, and non-research web content. Resources: search_type="resource" searches GitHub repositories, Hugging Face datasets/models, and Zenodo records that Lacuna has linked to at least one paper. To find benchmark or evaluation datasets, use search_type="resource" with resource_kind="dataset" (for example query "image classification benchmark" or a dataset name like "ImageNet"). resource_kind accepts codebase, dataset, model, or demo (one value or a list); provider accepts github, huggingface, or zenodo. Both filters require search_type "resource" or "all" (with either filter set, only resources are returned). Each result has an external `url`, a Lacuna `context_url`, and `linked_paper_count`; call get_resource on its id to list the linked papers (with their relationship to the resource), then get_paper on those papers for reported results and numbers. Resource search does not support date_from/date_to, venue, year sorting, or semantic ranking. ranking_profile accepts: - default / lexical (default): production ranking; relevance-sorted paper searches combine lexical and semantic retrieval when fields is unset. - semantic: conceptual paper retrieval; supported for paper and all. - bm25_title_abstract / bm25: lexical paper matching over those fields. sort accepts relevance (default), year_desc, or year_asc. Semantic ranking cannot use year sorting; constrain recency with date_from/date_to instead. date_from and date_to are inclusive YYYY, YYYY-MM, or YYYY-MM-DD bounds. author_id_or_url constrains a paper search to one author. Pass an author ID or Lacuna author page URL; it requires search_type="paper". fields optionally restricts and weights lexical fields, for example "title^4,abstract". Supported names are title, abstract, summary, concepts, name, top_names, and venue, plus description, topics, provider_key, and paper_titles for resources (a resource's title already includes its description, topics, README text, and linked paper titles). Fields must exist on the selected search_type, weights must be within 0 < weight <= 100, and fields cannot be combined with semantic ranking.

  ConnectorNo auth