"ADP" matching MCP tools:

• deep_researchA

  Seo Keywords AdsA

  ACCOUNT REQUIRED (free — sign in via GitHub at https://pipeworx.io/signup; depth:"thorough" needs a paid plan). If you are not signed in, use ask_pipeworx instead — it works on every tier. Grounded multi-source research across Pipeworx's 1517 STRUCTURED data sources (SEC filings, FRED/BLS economics, FDA, USPTO patents, markets, science, government records, etc.) in ONE call — this is NOT open-web search. Decomposes your question into focused facets, routes each to the right one of 5,798 tools IN PARALLEL, and returns a findings packet: verbatim evidence + confidence + source + fetched_at + a stable pipeworx:// citation per finding, with explicit gaps[] for facets the data couldn't answer (never invented). Best for broad/multi-part questions over structured data ("compare X and Y's regulatory + financial exposure", "research the filings + market picture for ACME"). For a single lookup use ask_pipeworx (one LLM call, not many). For BREAKING or colloquial CURRENT-NEWS / "what's the world saying about X" topics, prefer ask_pipeworx — it routes to live news APIs and the *-news-feeds packs; deep_research returns mostly empty gaps[] when the topic isn't in the structured catalog. Second-hop iteration: depth:"standard" re-angles unanswered gaps (gap recovery); depth:"thorough" additionally chases the best leads from the first pass — so multi-step questions resolve in one call. Every finding carries a `hop` field and a citation_uri — a resolvable pipeworx:// record URI, present only when the source emits one that resources/read can actually serve, so a citation you get back is always fetchable. "standard" and "thorough" also return contradictions[] flagging findings that disagree. Large records are semantically excerpted to the passages relevant to each facet (not head-truncated), so answers deep in a long filing/series aren't missed. Expect 15-60s (thorough with its follow-up + contradiction pass: up to ~90s).

  ConnectorNo auth

• report_content_issueA

  Fiveable for AP StudentsA

  Submit a content issue to Fiveable support only when the student explicitly asks to report it. This may lead to normal support follow-up. Do not automatically report disagreements or send conversation history, unrelated notes, or personal information. Fiveable resolves the content and reporter identity. Reuse requestId on retries.

  ConnectorNo auth

• goal-add-criterionA

  Planner (proof-of-done)A

  Append an acceptance criterion to a goal. The text must describe an observable check over an artifact (e.g. "GET /api/health returns 200 with {status:ok}"), not a subjective approval. Each criterion has a class: pre-merge (default — proved in CI / by attached evidence) or post-deploy (proved by an executable probe against the deployed prod instance). A post-deploy criterion MUST carry probeSpec {method, url, expect:{http_code, body:{field: expectedValue}}} — the request the runner sends and the answer it must get; without it the call is rejected with error=probe_required. Passing probeSpec alone implies probeClass=post-deploy. Grove mode: AC (class and probe included) can only be added while goal is in backlog (frozen once started), quality linter blocks high-severity issues. Standard mode: AC editable until goal is closed, linter is advisory. Returns criterion id, position, text, probeClass, probeSpec and any quality findings.

  ConnectorNo auth

• marketplaceA

  DETRAN AP: VeículoA

  The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

  ConnectorNo auth

• get_exam_resultsA

  Fiveable for AP StudentsA

  Read an owned completed exam using attemptId, or safely check a submitted exam using submissionId. Supply exactly one. Pending or partial grading returns status only, never unfinished scores or feedback. Honors practice resets and cannot dispatch scoring, finalize submissions or retrieve active exam content.

  ConnectorNo auth

• ask_pipeworx_groundedA

  Seo Keywords AdsA

  Hallucination-resistant answer mode for high-stakes reads. Same routing as ask_pipeworx — picks the right tool from 5,798 across 1517 sources, fills arguments, fetches the data — then EXTRACTS the answer using ONLY what the tool result contains. Returns {answer, evidence (verbatim quote), confidence, source, fetched_at, refusal_reason:null} on success, OR an explicit refusal {answer:null, refusal_reason:"not_in_source"|"no_tool_match"|"tool_error"|"data_truncated"|"llm_error"} when the data doesn't directly answer. Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts (financial verdicts, legal claims, medical lookups, public statements). Costs one extra LLM call vs ask_pipeworx — prefer ask_pipeworx for casual lookups.

  ConnectorNo auth

• connectA

  DETRAN AP: Impressão de CRLVB

  Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

  ConnectorNo auth

• marketplaceA

  MDA SEAD: Declaração de Aptidão ao PRONAF (DAP)A

  The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

  ConnectorNo auth

• authenticateA

  MPT AP e PA: Certidão Negativa de FeitosA

  MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

  ConnectorNo auth

• authenticateA

  Google AdsB

  MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

  ConnectorNo auth

• addA

  DomainCheckrA

  Adds two numbers and returns the sum.

  ConnectorNo auth

• addA

  webEmbeddingA

  Adds two numbers and returns the sum.

  ConnectorNo auth

• get_my_planA

  AdCreator AI Ad Headline GeneratorA

  For a connected AdCreator merchant: your current plan and price, and exactly what each higher plan adds (more videos, longer video duration) with pricing. Requires your AdCreator connection token. If not connected, it explains how to connect. Read-only.

  ConnectorNo auth

• explain_playerA

  Prediction Markets QuantA

  Explain WHY the 2026 draft board ranks a player where it does, factor by factor: projection, floor/ceiling band, boom/bust week shape, and the three separate ranks a board row carries — our model's own positional rank, the market's ADP, and the published blend between them — plus the edge between model and market. Also states what the projection does NOT model (injuries, camp news, schedule). Free, no key. Use for "why do you have <player> there", "explain <player> ranking", "what's driving <player>'s projection", "why is <player> a sleeper/bust". For a plain outlook or a verdict rather than the reasoning, use player_outlook.

  ConnectorNo auth

• who_do_i_draftA

  Prediction Markets QuantA

  Recommend the single best player to draft right now given the roster already on the user's team and their pick number, weighing positional need against the best value available (2026, any scoring format). The pick AND every alternative are free — no key, no email. Pro adds the reasoning behind each one. Prefer this mid-draft when the user asks "who should I take", "who do I draft", "what do I need". Input: roster (names on their team), pick_number, and optionally drafted (names already gone). Without drafted, the board is estimated from pick_number using consensus ADP. Returns one pick + a one-line reason.

  ConnectorNo auth

• goal-add-noteA

  Planner MCP — provable "done" for AI agentsA

  Add a free-form note (markdown supported) to a goal — decisions taken, dead ends hit, context worth carrying into the next session. Notes are NOT evidence: they hang off the goal rather than an acceptance criterion and never count toward AC coverage or closing a Grove goal — use goal-attach-evidence for proof. Notes are visible in the goal detail panel and returned by goal-get under notes[].

  ConnectorNo auth

• goal-add-criterionA

  Planner MCP — provable "done" for AI agentsA

  Append an acceptance criterion to a goal. The text must describe an observable check over an artifact (e.g. "GET /api/health returns 200 with {status:ok}"), not a subjective approval. Each criterion has a class: pre-merge (default — proved in CI / by attached evidence) or post-deploy (proved by an executable probe against the deployed prod instance). A post-deploy criterion MUST carry probeSpec {method, url, expect:{http_code, body:{field: expectedValue}}} — the request the runner sends and the answer it must get; without it the call is rejected with error=probe_required. Passing probeSpec alone implies probeClass=post-deploy. Grove mode: AC (class and probe included) can only be added while goal is in backlog (frozen once started), quality linter blocks high-severity issues. Standard mode: AC editable until goal is closed, linter is advisory. Returns criterion id, position, text, probeClass, probeSpec and any quality findings.

  ConnectorNo auth

• get_practice_questionsA

  Fiveable for AP StudentsA

  Returns original, course-specific multiple-choice practice questions. Free-text topics are matched against Fiveable's course map, so natural phrasing works. Omit topic to get balanced practice across the whole subject, with varied units, skills and stimulus formats. For history, science and language subjects this can return source-based sets — one stimulus with several questions off it — and stimulus images come back as viewable images. This is targeted or mixed practice, distinct from Fiveable's durable adaptive diagnostic. Every question carries a `Question id` that supports a saved answer submission for student progress. The recentCorrect and recentAnswered inputs allow the tool to drop to easier question types when a student is missing questions, helping find where understanding breaks down. A returned question set consumes one full-content preview unless existing access covers this practice feature. Moderate cost — roughly 300 tokens per question, more when images are attached.

  ConnectorNo auth

• get_study_planA

  Fiveable for AP StudentsA

  Reads one owned study plan, stable task ids, completion state and revision. Use its revision for task changes. Reading older plans never changes them.

  ConnectorNo auth

• get_exam_optionsA

  Fiveable for AP StudentsA

  Find Fiveable exam formats, access requirements and website links without questions or answer keys. Choose a subject for version choices; add unitNumber to verify that unit's current bank and standard format. With progress:read consent, includes only genuine server-saved continuation links. Browser-only progress is not remotely recoverable.

  ConnectorNo auth

• goal-add-evidence-textA

  Planner (proof-of-done)A

  SUBORDINATE / supplementary path — does NOT close an acceptance criterion. Adds a text-only note (URL to a permanent external source like CI run / GitHub commit / issue, or a description of a manual scenario) as extra context alongside the real proof. The path that actually covers an AC and closes a Grove goal is goal-attach-evidence — use that one for every criterion. Plain evidence NEVER counts toward AC coverage no matter how many you add; it is only a complement to an attached file. NOT for bytes — screenshots, logs, API responses, exports all go through goal-attach-evidence. NOT for filesystem paths — those need goal-attach-evidence with the actual file.

  ConnectorNo auth