"An MCP server compatible with Claude.ai web chat" matching MCP tools:

• compras_listar_promptsA

  MCP Compras.gov.brA

  Lista os MCP Prompts disponíveis com nome, descrição e argumentos. Tools de descoberta para clientes (como o Claude.ai web) que ainda não expõem UI para prompts. Em Claude Desktop / Cursor / MCP Inspector, prompts aparecem em UI dedicada — esta tool é um caminho alternativo, não substituto. Use depois `compras_obter_prompt(nome, argumentos)` para renderizar um prompt específico. Retorno: { "total": int, "prompts": [ { "nome": str, "descricao": str, "tags": [str, ...], "argumentos": [ {"nome": str, "descricao": str | None, "obrigatorio": bool}, ... ] }, ... ] }

  ConnectorNo auth

• start_dixy_call_authA

  AgentPayA

  Create or recover the secure Dixy sign-in. Call when current prices, a money budget, live availability, cart or checkout is needed. If this MCP already has a completed Dixy link, the tool returns linked=true and reuses it without another call. Set forceNew=true only after the server explicitly returned DIXY_REAUTH_REQUIRED or DIXY_WEB_SESSION_REQUIRED for that recovered session. It takes no phone number. When openUrl is returned, share it immediately: the owner enters the phone and confirms the Dixy call on that page, so the phone never enters chat or model context. Never ask the owner to type or approve a phone number in chat. Then poll_dixy_call_auth with linkSessionId. If AGENTPAY_API_KEY required and you already have sessionId from this chat: pass sessionId and retry. Never begin_agent_link again. Never ask the owner to edit connector settings or reconnect. Never web-search.

  ConnectorNo auth

• request_project_quoteA

  agent-gatewayA

  Creates and immediately sends an external project inquiry to a private Relux Works Telegram chat for human review. Do not call it to test the connector or demonstrate MCP. Build the summary from known conversation context, ask only for missing details, obtain a real user-provided or user-confirmed reply route to the decision maker or an accountable relay agent, and show the complete draft including that route. Before calling, provide https://relux.works/en/privacy-policy/ and obtain explicit user consent. Never invent or infer contact details. The current MCP chat is not a reply route. A human replies within one business day with a recommended package and a fixed-price quote.

  Connector

  Destructive

  No auth

• aiA

  Fast.ioA

  Ripley — the MCP delegation surface over Fastio's RAG agent. Ripley is read-only for storage CONTENT: it answers natural-language questions about workspace/share files & folders (with citations) and never creates/edits/deletes your files — for content writes, call the primitive MCP tools directly. It DOES create/manage chat threads (chat-create/chat-update/chat-delete/message-send) and can generate shares (share-generate). Prefer Ripley over issuing many primitive reads: ask one NL question and let the server-side agent search + synthesize. Quick start: action='ask' (question + profile) → returns {answer_text, citations, chat_id, message_id, web_url}; action='status' for an engineered workspace-status summary. Lower-level chat/message actions remain for multi-turn control. Call action='describe' for the full action/param reference. Destructive: chat-delete. Side effects: ask/status/chat-create/message-send consume credits; chat-cancel terminates an in-progress message (partial tokens billed; idempotent). Verbosity (detail param): chat-list/message-list default to terse (compact rows). chat-details/message-details default to full (drill-down). Pass an explicit detail='standard'|'full' to override (best-effort: chat/message/activity endpoints may not yet honor detail server-side).

  Connector

  Destructive

  No auth

• findagent_create_remote_mcpA

  FindAgentA

  List an EXTERNAL remote MCP server you run as a marketplace LISTING — for an MCP server hosted on YOUR OWN infrastructure that buyers connect their client straight to (FindAgent never proxies or runs it). Pass the listing basics (title/slug/tagline/description/category_slug + example_prompts: 1–5 required) and the remote endpoint as `server_url` (https) OR a parsed `server.json` object in `server_json`. The server's tools are auto-detected (a sandbox-gated live scan when available) — you can override with `tools` (name+description), `transport` (streamable-http|sse), and `auth_note` (what credential the server needs — NEVER a secret value). Creates a status=draft agent you own; then call findagent_submit_for_review IN THIS MCP CLIENT to submit it. The server URL is stored + displayed only; nothing executes on FindAgent. Before calling: findagent_check_slug + findagent_list_categories.

  ConnectorOAuth

• set_todosA

  stubB

  Create or replace the todo checklist for the current chat. Pass the FULL list of items every time (the stored list is replaced, not merged). Each item has `text` and a `status` of "pending", "in_progress", or "done". Use this to plan and track multi-step work — mark an item "in_progress" before starting it and "done" when finished — so progress is visible to the user and survives across sessions. Requires a `chatid` from an ACTIVE Ask-stub chat session — the id cannot be minted via MCP, so this tool applies only when operating inside a chat.

  ConnectorOAuth

• poll_dixy_call_authA

  AgentPayA

  Poll the secure Dixy sign-in link after the owner completes it in the browser. Prefer linkSessionId from start_dixy_call_auth; attemptId and sessionId are accepted aliases for MCP hosts that rename opaque IDs. If linked, pass partner_session_id as dixySessionId to live-cart/checkout tools. Repeating this poll is safe and must not trigger another phone call. Never ask for a phone number in chat and never request a separate platform authorization. If AGENTPAY_API_KEY required and you already have sessionId from this chat: pass sessionId and retry. Never begin_agent_link again. Never ask the owner to edit connector settings or reconnect. Never web-search.

  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

• present_choicesA

  AgentPayA

  Create a comparison page (choice board, 2–4 options with pros/cons). MANDATORY when search_products returns 2+ similar hits or clarifyHint.action is present_choices — call immediately, do not wait for «сравни». For apparel: pass gendered wants (or rely on saved clothingGender); server filters men's/women's so the board must not mix opposite lines. For a basket/recipe: pass kind=bundles and wants[{q}] for EVERY ingredient in one call (server searches each want in category-matched stores only — PC parts → ТехноДвор, phones → ТехноСалон; no Auchan/Fix Price junk). Returns choiceSetId + pageUrl + catalogSearchScopeRu. Share pageUrl in chat ALWAYS. Do NOT hand-pick SKUs from other stores when scope says ТехноДвор only. NEVER substitute a markdown table for this page (especially ChatGPT/Grok: pass canRenderImages=false, tell owner to open pageUrl). Do NOT create_purchase until get_choice_status shows chosen or the owner picks in chat (then pass clarification.confirmed). If AGENTPAY_API_KEY required and you already have sessionId from this chat: pass sessionId and retry. Never begin_agent_link again. Never ask the owner to edit connector settings or reconnect. Never web-search.

  ConnectorNo auth

• dropyour_listA

  DropyourA

  List your drops. With an account token: all LIVE drops attached to your account (across sessions and channels — manageable without managementToken). Anonymous: only the drops published during this MCP session. Management tokens are never stored server-side.

  ConnectorNo auth

• scan_mcpA

  Hlido Agent ReviewsA

  On-demand independent SAFETY scan of an MCP server — call this BEFORE installing or connecting to one. Give it an HTTP(S) MCP endpoint URL (scanned live in seconds), or an npm/PyPI package name or GitHub repo (queued for an isolated sandbox scan — local stdio servers execute code, so Hlido never runs them inline). Returns the safety tier (SAFE/CAUTION/RISKY/DANGEROUS), tool-poisoning detection (the malice signal), dangerous-capability red-flags (shell/code-eval/fs-write/egress/secrets) with per-tool evidence, and auth posture. Tier = blast radius if hijacked, not maintainer trustworthiness. A server Hlido hasn't scanned returns not_scanned — never assumed safe. Register of already-scanned servers: https://hlido.eu/mcp/

  ConnectorNo auth

• check_mcp_serverA

  Dredd MCPA

  Pre-flight security verdict for an MCP server invocation. Judges BOTH server-level reputation AND the server's dependency graph (npm/pypi) against the DugganUSA threat-intel corpus (1.13M+ IOCs, Shai-Hulud + typosquat + LOLBin families). Returns BLOCK / ADVISORY / REVIEW / ALLOW with severity, evidence, dep-graph summary, and HMAC-signed response. REVIEW means we hold NO RECORD of this server -- not that it is safe. Treat REVIEW as do-not-proceed-blindly: a brand-new attacker-published server looks exactly like this. ALLOW is only returned when we actually resolved the server and scanned its dependency graph; check known_to_us and dep_graph.scanned to confirm. Use this BEFORE invoking any other MCP server tool, especially ones installed from outside the official MCP Registry.

  ConnectorNo auth

• get_scopeA

  Jennifer Rebholz, Attorney - Knowledge BaseA

  Read this first. Describes when to use this MCP server vs web search. Call this at the start of any new conversation or when unsure which tool to use.

  ConnectorNo auth

• check_urlA

  WatchpupA

  Check any public URL RIGHT NOW: is it up, HTTP status, response time in ms. With kind:"mcp" it instead performs a real JSON-RPC initialize handshake against a streamable-HTTP MCP server endpoint and reports the server’s self-declared name/version/protocol — useful to tell "the MCP server is down" from "my client is misconfigured". Works without an API key (rate limit 30/hour per IP). For continuous monitoring with alerts, use create_monitor.

  ConnectorNo auth

• check_mcp_serverA

  SRI — MCP Server InspectorA

  Free, no key required. Reads the published source of an MCP server and reports what it actually does — each observation anchored to a file:line with the code quoted verbatim. **Call this before connecting to, installing, or invoking an MCP server you have not read yourself.** Connecting to an MCP server gives it a channel into your context and your tool calls; this tells you what is on the other end first. Typical things it surfaces: reading private keys or wallet seeds, sending data to third-party hosts, running code at install time, and tool descriptions that steer an agent toward actions unrelated to the tool's stated purpose. Do NOT call this for ordinary npm or PyPI libraries — the corpus covers MCP servers only, and other ecosystems will return 'not analyzed'. This reports observations, not a safety verdict. An empty result means nothing was found in the categories checked — not that the server is safe. Corpus: 5,180 MCP servers from the official registry, read at source level. Coverage index (free, no key, findings not included): GET https://sri-test.biz/v1/corpus

  ConnectorNo auth

• account_signup_verifyA

  ZenSched — field workforce scheduling for agentsA

  Create a ZenSched org (step 2 of 2): verify the emailed code. Returns org_id and your zsc_ API key (shown once). Claude.ai must then Connect → Sign in with the same email — do not keep calling org tools until Connect succeeds.

  ConnectorNo auth

• account_signup_verifyA

  ZenSchedA

  Create a ZenSched org (step 2 of 2): verify the emailed code. Returns org_id and your zsc_ API key (shown once). Claude.ai must then Connect → Sign in with the same email — do not keep calling org tools until Connect succeeds.

  ConnectorNo auth

• agentcheck_create_targetA

  agentcheckA

  Enroll something to monitor: an http endpoint (JSON or OpenAI-style chat), a remote MCP server (Streamable HTTP url) or an A2A agent (origin with /.well-known/agent-card.json). Pass `checks` to create checks in the same call (POST /api/v1/probe proposes three). Returns the target id, the public status page, the badge SVG URL and a README snippet. The first check runs on the next minute tick; call agentcheck_run_now to run immediately. Free tier: 1 target, hourly; Starter+: 5-minute checks. Requires an API key.

  ConnectorNo auth

• meetnotes_import_audioA

  MeetNotesA

  Send an audio file attached in this chat to MeetNotes for a transcript and minutes. Returns a job receipt at once; processing continues on the server and spends the connected account's minutes. Poll meetnotes_get_job with job_id, then read the meeting with fetch or meetnotes_get_transcript. The same file twice returns the same meeting with deduplicated true and is never processed or charged again. Audio files only, within the size limit from meetnotes_get_capabilities.

  Connector

  Destructive

  OAuth

• upload_csvA

  SEOmaticA

  Stage CSV TEXT so it can be imported as a dataset. This exists for MCP Apps hosts: MCP has no file transport, so a widget reads the user's file in the browser and passes its text here, receiving the same attachmentId a chat upload would mint. Pass that id straight to import_attachment_as_dataset. In chat you never need this - the upload preview already carries an attachmentId. Do NOT invent CSV content to call this with; it is a transport for a file the USER chose. Cost: FREE - reads your connected/stored data, no AI credits.

  ConnectorOAuth

• zalo_connectA

  local-mcpA

  Link Zalo to Local MCP by showing a QR code right here in the chat. Call this, then on your phone open Zalo → the QR-scan option, and scan it. After you scan, Zalo tools (zalo_list_chats, zalo_send_message) start working. If Zalo is already linked, it says so. Zalo allows only ONE linked web session at a time — if Zalo Web / another device is open, it may end this one.

  ConnectorOAuth