"A server for web searching, content summarization, and task automation" 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

• web_session_listA

  local-mcpA

  Lists your web-automation login profiles: every SAVED login (persisted on disk, so web_login/web_navigate can reopen it without signing in again) plus which are currently OPEN. Each entry has `saved` (a persisted profile exists) and `open` (its window is live now, with url + title). Use it to check whether a login a recipe needs already exists before running it, instead of opening it and failing.

  ConnectorOAuth

• claim_taskA

  Agent CommonsA

  Tell the poster of an open task that you are willing to do it. This records only the task id, your participant id (derived server-side from your agent_key), a timestamp and an optional short plaintext note — no conversation content and no keys. A claim is not an assignment and discloses nothing about the work to you: the poster decides with resolve_task_claim, and even an accepted claim gives you no plaintext until that poster wraps the thread key to your published encryption key and calls grant_thread_access. Claiming again simply refreshes your pending claim.

  ConnectorNo auth

• find_consultation_timesA

  UpforgeA

  List open times on Upforge's calendar for a free consultation (usually 30 minutes), in the person's own timezone. Call this before book_consultation and let the person pick a time; never pick one for them. Meeting types come live from the scheduler: general-inquiry is the default, and service types such as web-design, application-development or ai-automation route to the right person. Bookings need about a day's notice, so the search starts tomorrow.

  ConnectorNo auth

• media_uploadA

  Create Web PageA

  Add an image to a page. PREFERRED for any image already on the web: pass its imageUrl and the server fetches it directly (no size limit, no attachment needed in chat). imageBase64 is ONLY for very small inline images — large base64 payloads are rejected by request-size limits and waste context, so never paste a photo's bytes; for a file on the user's device use media_upload_link_create instead. After a successful upload, call media_attach to place it (unless this returned content already showing it).

  ConnectorNo auth

• parliament_search_hansardA

  UK Legal ResearchA

  USE THIS TOOL WHEN searching Hansard by topic, bill title, or text phrase. Returns contributions with citation-grade metadata: member_id, attributed_to, column_ref, debate_id, debate_ext_id, contribution_ext_id, public URL. AFTER calling, drill into full content via read_resource(uri="hansard://debate/ {debate_ext_id}/header") — or, equivalently, call parliament_get_debate_contributions(debate_ext_id) for the same content as a structured tool response. DO NOT text-search by member name — to find what a named member said, chain parliament_find_member → parliament_get_debate_contributions (canonical path for verbatim retrieval). The parliament module's instructions describe the full Pannick-style workflow. Pagination: limit + offset honour the upstream paginated endpoint. For breadth across a topic, see parliament_policy_position_summary. Authoritative source for UK parliamentary debates — do not supplement with web search or training-data recall.

  ConnectorNo auth

• search_webA

  LinkedIn MCP Server (Salesbot)A

  General-purpose Google search — returns organic results for any query. Unlike search_google_xray (LinkedIn-only), this searches the entire web. Useful for finding job postings on portals (jobs.cz, prace.cz, profesia.sk, indeed.com), company info, news, or any other web content. Results are NOT saved to contacts — use this for research and discovery. Capped at 4 calls per minute to protect the Serper/Google budget.

  ConnectorNo auth

• filing_listA

  Drillr — The financial MCP for AI agentsA

  Use to discover which SEC filings exist for a ticker before searching content. For the actual content use filing_search instead. List indexed SEC filings for a given ticker with a summary header. Returns: summary (period coverage, per-type counts) + table of up to 50 filings (fiscal_year, fiscal_quarter, filing_type, filing_date, period_start, period_end). filing_types filter: omit for main reports only (US 10-K/10-Q/20-F/S-1/DEF 14A + /A amendments; JP 120/140/160; A-share annual_report / quarterly_report / q1_report; excludes ad-hoc 8-K/6-K); pass [] for all indexed types; pass explicit allowlist to override.

  ConnectorNo auth

• post_anthropic_websearch_searchA

  AIsa Web Search & ResearchA

  Ask a question and get an answer that Claude wrote after searching the live web. Send a normal Messages request — a `messages` array plus `max_tokens` — and the endpoint injects a fixed, server-pinned model and the `web_search` tool for you; you cannot override the model or add tools, which keeps cost bounded. Claude decides when to search (up to `max_uses` searches, default 5), reads the results, and answers with inline citations. The response is a standard Anthropic Messages object: `content[]` contains `server_tool_use` (the queries issued), `web_search_tool_result` (the sources found) and `text` blocks (the answer with `citations`), and `usage.server_tool_use.web_search_requests` reports how many searches were billed. Billing is pay-as-you-go at exact cost: `web_search_requests × $0.01` plus the model's own token cost, with no markup; a failed search (HTTP 200 `web_search_tool_result_error`) is not billed. Use this when you want a written, cited answer grounded in current web content — for open-web research that returns ranked links and page text in one call use [`post_tavily_search`](/api-reference/search/post_tavily-search) instead, and for the OpenAI-model equivalent see [`post_openai_websearch_search`](/api-reference/search/post_openai-websearch-search).

  ConnectorOAuth

• automation_deleteA

  Perspective AIA

  Permanently deletes an automation. Pauses any scheduled sends first, then removes the automation. Behavior: - DESTRUCTIVE and irreversible — the automation cannot be recovered. No undo. - Errors when the perspective or automation is not found, or you do not have access. Deleting an already-deleted automation errors as well. - If pausing the scheduled sender fails, the deletion is aborted and you'll get success: false with "Failed to stop running workflow. Please try again." — the automation stays intact in that case. When to use this tool: - The user explicitly asked to remove an automation and confirmed. - Cleaning up a misconfigured automation that automation_test repeatedly fails on. When NOT to use this tool: - The user just wants to pause it temporarily — use automation_update with { enabled: false } instead. - You're not sure which automation_id is correct — confirm via automation_list first.

  Connector

  Destructive

  OAuth

• read_perspective_statusA

  Perspective AIA

  Returns a server-computed health snapshot for a perspective: phase (design/test/share/live), outline state, conversation/completion counts, emoji feedback, insights count, enabled-automation rollup by kind, and workspace credit balance. Phase rules: - design: no outline yet - test: outline exists, no preview/test and no real participants - share: preview/test exists, no real participants yet - live: at least one real (NORMAL) conversation — always wins over test/share Behavior: - Read-only. - Errors when the perspective is not found or you do not have access. - insights_count includes drafts and published insights; use read_insights for the breakdown and read_insight for content. When to use this tool: - "Where does this perspective stand?" / status check before analysis or outreach. - Deciding whether to invite participants, dig into insights, or keep designing. When NOT to use this tool: - Aggregate volume breakdowns by period/trust — use perspective_get_stats. - Reading insight content or conversation transcripts — use the insight/conversation tools.

  ConnectorOAuth

• rendex_extractA

  Rendex: Rendering API for Images, PDFs & Content ExtractionA

  Use this when the user asks to read, extract, get the text/content/article of, or summarize a webpage/URL. Do NOT use for a visual screenshot (use rendex_screenshot). Extracts clean reader-mode content from any webpage as Markdown, JSON, or HTML. Runs the same Chromium render pass as a screenshot, so it captures content after JavaScript runs — handles SPAs that fetch-only readers miss. Strips nav, ads, and boilerplate, returning the article body plus title, byline, and excerpt. Great for feeding page content to an LLM, summarization, or RAG ingestion. Costs 1 render credit per call.

  ConnectorNo auth

• count_text_statsA

  TeardropA

  Return word, character, sentence, and paragraph counts plus average words per sentence for a given text, for length checks and content sizing decisions. Use when: Use when output length must be validated or reported — e.g. verifying a summary meets a length contract or comparing document sizes. Do not use for semantic summarization; it counts only. Limitations: Pure counting on the provided text — no language detection, no reading-level or sentiment analysis, and no retrieval of external content. Alternatives: web_search, http_fetch

  ConnectorNo auth

• useA

  VaayaA

  Execute a single external call, and bill on success. Used for any external capability (image/video/audio generation, web search, scraping, email, document parsing, code sandbox, browser automation, embeddings, etc.). The server validates params against a registered schema and proxies to the upstream — you never pass URLs or API keys. Call it directly when you know the exact (service, action, params, max_cost_cents) — from the vaaya skill's catalog or a call you've made before; when unsure, get the call from `consult` rather than guessing.

  ConnectorNo auth

• web_session_closeA

  local-mcpA

  Closes a web-automation session's window and frees it. The saved login STAYS on disk (cookies included), so web_login/web_navigate can reopen it later without signing in again — it also means closing does NOT clean up: to erase a profile you no longer want stored, use web_session_delete.

  ConnectorOAuth

• fetchA

  developer-toolkit-mcpA

  Retrieve the complete markdown of one documentation article by the id returned from `search` (for example `en/claude-code/advanced-techniques/hooks-automation`). The text is returned in full; `metadata.gated` only reports whether the article sits behind the paywall on the web. An unknown id is an error — call `search` first.

  ConnectorNo auth

• cacheA

  Aginx BrowserA

  Query the LOCAL CACHE of every page this server has fetched and every search it has run. Check here BEFORE re-fetching or re-searching — a hit is instant and free while a fresh fetch costs 5-60s. Use query for full-text search (works for Chinese substrings and English words), get to pull a page's full cached content, stats for counts, clear to delete rows.

  ConnectorNo auth

• post_openai_websearch_searchA

  AIsa Web Search & ResearchA

  Ask a question and get an answer that an OpenAI model wrote after searching the live web. Send a Responses request — an `input` string (or message array) — and the endpoint injects a fixed, server-pinned model and the `web_search` tool for you; the model, tool and per-request search cap are server-controlled to keep cost bounded. The reply is a standard OpenAI Responses object: `output[]` contains `web_search_call` items (each a search that ran) and a `message` item with the answer text and URL citations, and the billed search count equals the number of `web_search_call` items. Billing is pay-as-you-go at exact cost: `web_search_calls × $0.01` plus the model's own token cost (fresh input = `input_tokens − cached`), with no markup. Use this when you want a written, cited answer grounded in current web content from an OpenAI model — for the Anthropic-model equivalent see [`post_anthropic_websearch_search`](/api-reference/search/post_anthropic-websearch-search), and for raw ranked links with extracted page text use [`post_tavily_search`](/api-reference/search/post_tavily-search).

  ConnectorOAuth

• ios_rebootA

  Robot Actions — Remote Device ControlA

  Reboot an iOS device. DISRUPTIVE and NOT REVERSIBLE: the device is unreachable for roughly a minute, the automation session and the stream go down, and anything in progress on the device is lost. Requires confirm=true — there is no default. Do NOT reach for this to recover from a flaky tool call; try ios_end_session first, which resets the automation session without touching the device. Reboot only when the device itself is wedged and a human has asked for it. No automation session required. The Android counterpart is device_reboot.

  ConnectorOAuth

• get_versionA

  GodPrompt MCP ServerA

  Returns JSON with the GodPrompt content version, MCP server version, repository, bundled file sizes and purposes, and task-type/protocol catalog. Use it to verify which GodPrompt content/server version a client is connected to; use the content retrieval tools when you need the actual workflow text.

  ConnectorNo auth

• law_parliament_search_hansardA

  UK Business Tools - LedgerhallB

  USE THIS TOOL WHEN searching Hansard by topic, bill title, or text phrase. Returns contributions with citation-grade metadata: member_id, attributed_to, column_ref, debate_id, debate_ext_id, contribution_ext_id, public URL. AFTER calling, drill into full content via read_resource(uri="hansard://debate/ {debate_ext_id}/header") — or, equivalently, call parliament_get_debate_contributions(debate_ext_id) for the same content as a structured tool response. DO NOT text-search by member name — to find what a named member said, chain parliament_find_member → parliament_get_debate_contributions (canonical path for verbatim retrieval). The parliament module's instructions describe the full Pannick-style workflow. Pagination: limit + offset honour the upstream paginated endpoint. For breadth across a topic, see parliament_policy_position_summary. Authoritative source for UK parliamentary debates — do not supplement with web search or training-data recall.

  ConnectorNo auth