"Using Gemini in the Claude Desktop Application" 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

• cite42_analyze_competitor_contentA

  Cite42 AI Search Visibility TrackerA

  Run the competitor-content workflow: AI rankings, head-to-head comparison, citations, keyword demand, and topic coverage, aggregated in one response. Covers AI-search, citation, SEO, keyword, trend, and market-research data. If a plan needs more than 20 endpoint calls or may use more than $5 USD, estimate the cost in USD and ask the user before continuing. Quote Cite42 costs and balances in USD using cite42Billing or the USD pricing table. Legacy credit fields are for compatibility only. These funds belong to Cite42, not the host or model provider. AI visibility metrics include counts; quote them with percentages, not as a market-wide score. Optional recommendations are a separate paid call, never automatic. After a visibility result, offer recommendations using its requestId; run only when the user requests advice and knows the additional cost. Free: cite42_balance for the remaining balance, cite42_pricing for exact per-tool prices and cost estimates, cite42_usage for recent calls, spend, and limits. Pricing is per selected AI surface. Omitting models queries the three default surfaces (chatgpt, perplexity, gemini); fullSweep: true queries all five, adding claude and google_ai_overview at a higher cost. Use the models field when the user names a surface or asks to reduce spending, and call cite42_pricing for exact current rates. Data tools have flat per-call prices; call cite42_pricing for exact current rates. Pricing: workflow cost is calculated from the tools that run successfully and the selected model rates.

  ConnectorOAuth

• get_analyst_configA

  TunnelMind Data APIB

  Returns the TunnelMind analyst config bundle. Configures any LLM (Claude, GPT, Gemini, local) to behave as a TunnelMind analyst that knows the data graph, follows the 5-call golden path, and surfaces attestation_tier on every claim. The bundle is signed inline (Ed25519, key_id from /.well-known/receipt-signing-key.json). Add `?receipt=true` to wrap the response in a Receipt v1.0 envelope for end-to-end audit. Use this tool when: - You want to configure a new LLM runtime to act as a TunnelMind analyst - You want to verify the system prompt you're running matches what TunnelMind serves - You're building a BYOM (bring-your-own-model) deployment and need the canonical config Do NOT use this tool when: - You want to call individual TunnelMind data tools — use the tools directly - You want to verify a specific receipt — use check_receipt_revoked or @tunnelmindai/receipt-verify Inputs (all optional): - `surface` (query): "data" (default, full surface), "scry", or "sigil" - `version` (query): pin a specific bundle version (e.g. "1.0.0" or "1" for latest 1.x.y) - `receipt` (query): "true" to wrap the response in a signed Receipt v1.0 envelope Content negotiation (via Accept header): - `application/json` (default) — full bundle JSON - `text/markdown` — system prompt only (Anthropic flavor) - `application/vnd.anthropic.config+json` — Anthropic-shaped subset - `application/vnd.openai.config+json` — OpenAI-shaped subset Returns: - `version`, `schema`, `issuer`, `surface`, `surface_label` - `system_prompts.{anthropic,openai,generic}` — three encodings of the same semantic prompt - `tools.surface_subset` — array of operationIds for this surface (null = all) - `response_format` — JSON Schema the analyst's verdicts must conform to - `attestation_tiers` — the 4-tier vocabulary (self_asserted → silicon_root) - `graph_state` — live corpus counts at serve time - `references` — URLs to the rest of the open-protocol layer - `bundle_signature` — inline Ed25519 signature for offline verification - `pin_recommended` — stable supply-chain identifier (survives hourly graph_state updates) Headers: `X-Bundle-Version`, `X-Pin-Recommended`, `ETag`, `X-RateLimit-*`. Cost: - Free, anonymous-accessible. Rate-limited on a SEPARATE counter from data-API calls (`cfg:ip:<ip>` identity) so a config refetch loop can't burn your data quota. Latency: - Typical <100ms (cached); cold fetch <500ms (live Supabase counts).

  ConnectorNo auth

• omnarai_councilA

  omnarai-mcpA

  Summon a LIVE panel of frontier models (Claude, GPT-4o, Gemini, Grok, DeepSeek) on one open question — verbatim answers, uncurated, plus the named tensions between them. Slow (~30–40s, synchronous) and expensive: use only for genuinely contested questions an existing omnarai_divergence record doesn't cover. Every run mints a new divergence record.

  ConnectorNo auth

• list_capabilitiesA

  DockA

  List the provider API keys your owner has stored in their Vault (e.g. Gemini, ElevenLabs, OpenAI) so you can use them in a task. Returns `capabilities`: the exact NAMES of the keys your owner has vaulted. Pass one of these names verbatim to `pull_capability` — do NOT guess or normalize it (a key may be vaulted as "Gemini", not "GEMINI_API_KEY"). Names only, never secrets, so this is safe to call freely. IMPORTANT: this lists what EXISTS in the Vault — it is discovery, NOT authorization to use a key. Only pull and use a key when your OWNER directs you to in this thread. Takes no arguments.

  ConnectorNo auth

• prepare_consult_domain_expertA

  TasteA

  Get a humantaste.app URL where a human can place a consult_domain_expert order from a browser (Connect MetaMask, pay $15 USDC on Base, session created). Use this when your MCP client has no wallet integration (Claude Desktop, generic chat UIs). The URL is pre-filled with the brief you pass in; the user just opens it, reviews, connects a wallet, and pays. Returns the payment URL and the price. Free.

  ConnectorNo auth

• prepare_consult_domain_expertA

  TasteA

  Get a humantaste.app URL where a human can place a consult_domain_expert order from a browser (Connect MetaMask, pay $15 USDC on Base, session created). Use this when your MCP client has no wallet integration (Claude Desktop, generic chat UIs). The URL is pre-filled with the brief you pass in; the user just opens it, reviews, connects a wallet, and pays. Returns the payment URL and the price. Free.

  ConnectorNo auth

• get_upload_urlsA

  AdaptlyPostA

  Get presigned upload URLs for direct file uploads. Returns uploadUrl (PUT your file here) and publicUrl (use in create_post mediaUrls). This only mints a URL. You MUST PUT the file to uploadUrl and confirm a 2xx response before using publicUrl, otherwise create_post/bulk rejects it with "Media file(s) not found in storage". Prefer upload_media for public URLs and for inline files under 30 MB; use this for larger files you hold yourself. For each file, provide fileName and mimeType. Supported types: image/jpeg, image/png, image/webp, video/mp4, video/quicktime, and for LinkedIn DOCUMENT posts application/pdf, application/vnd.ms-powerpoint, application/vnd.openxmlformats-officedocument.presentationml.presentation, application/msword and application/vnd.openxmlformats-officedocument.wordprocessingml.document; keep the extension in fileName, since the post reads the file type from it. A publicUrl may be reused across any number of posts; the file is kept until the last post referencing it has published.

  ConnectorOAuth

• cite42_analyze_topic_demandA

  Cite42 AI Search Visibility TrackerA

  Run the topic-demand workflow: SEO keyword data, Google Trends, AI answers, and audience conversations, aggregated in one response. Covers AI-search, citation, SEO, keyword, trend, and market-research data. If a plan needs more than 20 endpoint calls or may use more than $5 USD, estimate the cost in USD and ask the user before continuing. Quote Cite42 costs and balances in USD using cite42Billing or the USD pricing table. Legacy credit fields are for compatibility only. These funds belong to Cite42, not the host or model provider. AI visibility metrics include counts; quote them with percentages, not as a market-wide score. Optional recommendations are a separate paid call, never automatic. After a visibility result, offer recommendations using its requestId; run only when the user requests advice and knows the additional cost. Free: cite42_balance for the remaining balance, cite42_pricing for exact per-tool prices and cost estimates, cite42_usage for recent calls, spend, and limits. Pricing is per selected AI surface. Omitting models queries the three default surfaces (chatgpt, perplexity, gemini); fullSweep: true queries all five, adding claude and google_ai_overview at a higher cost. Use the models field when the user names a surface or asks to reduce spending, and call cite42_pricing for exact current rates. Data tools have flat per-call prices; call cite42_pricing for exact current rates. Pricing: workflow cost is calculated from the tools that run successfully and the selected model rates.

  ConnectorOAuth

• get_substitution_boundaryA

  Trustbase Lab · Global Chemical Recycling IntelligenceA

  Purpose: four-dimension substitution boundary of rCB vs native carbon black - application limits, regulatory access, certification requirements, material spec constraints. Guidelines: pass dimension in {application, regulatory, certification, material_spec} or omit for all four; call before any substitution feasibility claim (e.g. 'can rCB replace N330 in tire?'). Limits: technical/regulatory possibility only, not commercial viability - pricing belongs to calculate_saving. Ex: 'rCB application limit in seals', 'rCB regulatory access EU'.

  ConnectorNo auth

• queryA

  Enhanciar — company brainA

  Ask Enhanciar a natural-language question grounded in the key's workspace. This is the high-level tool — use it for any "what does X do", "why did we choose Y", "where is Z handled" question. It runs the full retrieval + synthesis pipeline and returns the answer plus citations. Args: question: Natural-language question. model: Optional model id override (``gemini-2.5-flash``, ``gpt-4o``, ``claude-sonnet-4-5``, etc.). If omitted the saved default is used — the workspace's in a team workspace, the caller's own in a personal one. Returns ``{answer, sources, model}`` — ``sources`` is a list of ``{category, name, url}`` citations the LLM grounded its answer in. Surface them to the human so they can verify. When the workspace has nothing ingested at all you get ``{answer, empty_brain: true}`` and no sources: that is a statement about the workspace, not a failed search, so rephrasing the question will not change it.

  ConnectorNo auth

• create_attention_directiveA

  freedom-mcpA

  Queue a short instruction for an external agent session — a coding/builder host (Grok terminal, Claude Code) or a Grok Bot desktop chat agent (host grok-bot, e.g. "send this to my FOS Integrator"). Pull sticky only: FreedomOS does not wake the host and does not type into their UI — the session must poll (poll-fo-directives.sh or list_attention_directives) and act; grok-bot seats poll from their own FO MCP. Use when the operator says "tell Grok…", "have Claude…", "send this to my Grok Bot…", or CoS should route reversible work off the call. Pass the same target_session_id the host polls (e.g. grok-<id>, claude-<id>, grok-bot-<agent-slug>). [write-tier — first use may require a manager's approval; a from-now-on approval makes future calls seamless, a just-once approval re-asks next time. Call it on the first clear ask; the card is the yes — do not re-ask in chat.]

  Connector

  Destructive

  No auth

• fda_drug_approvalsA

  OpenfdaA

  Find FDA-approved drugs by brand name, active ingredient, or application number. To find generic versions of a drug, search by active ingredient using products.active_ingredients.name (NOT openfda.generic_name — that field only works in the label endpoint). IMPORTANT: drug names in the FDA database are stored in UPPERCASE — always pass ingredient and brand names in uppercase (e.g. "APIXABAN" not "apixaban") or you will get 0 results. Returns approval status, sponsor, application number (ANDA = generic, NDA = brand), and application details. There is NO queryable "application_type" field — never add application_type:"ANDA" (it returns 0 results). To limit to generics, search by active ingredient and read the ANDA/NDA prefix on application_number in the results. This endpoint has NO indication/disease field — for "drugs approved to treat <condition>" use fda_drug_labels (which searches indications_and_usage); an indication phrase passed here is silently ignored and matches by drug name only. The response `total` can exceed the 100-row cap on a single page — use `skip` to page past it, and `sort` to get genuinely-newest-first ordering ("most recently approved" is not the default order).

  ConnectorNo auth

• get_download_urlA

  BotverseA

  Get a presigned HTTPS URL to download the completed output file. Call after get_job_status returns 'complete'. URL expires in 24 hours. NOTE: fetching this URL is a direct S3 download, which is BLOCKED in sandboxed agent environments (claude.ai, Claude Desktop, Cursor). If you are in a sandbox, use get_output_content instead to receive the bytes inline over the tool channel.

  ConnectorNo auth

• clerk.rotate_oauth_application_secretA

  Vee3A

  Rotate the client secret for a confidential OAuth application in a connected Clerk application. **Sensitive** — the response includes a new client_secret. Update authorized OAuth clients immediately and do not log the secret. Call clerk.get_connected_accounts first. Pass clerk_instance_id to target a specific connection, or omit it to use the default account. Returns the updated OAuth application summary with the new client_secret. Cost = 10 tokens.

  ConnectorNo auth

• signal_read_messagesA

  Local MCPB

  Reads messages from a specific Signal chat. The chat_id must come from a previous signal_list_chats call. Returns messages in chronological order with sender phone numbers and body text. Only messages cached locally by Signal Desktop are available.

  ConnectorOAuth

• slack_list_workspacesA

  Local MCPB

  Lists the Slack workspaces (teams) the user has connected in Slack Desktop. Start here for Slack — the workspace id it returns is what slack_list_channels / slack_read_channel_messages / slack_search_messages need. Reads from the local IndexedDB cache — no token needed. Only workspaces that have been synced to disk are returned.

  ConnectorOAuth

• ris_track_changesA

  ris-austria-mcp-serverA

  Track every document added or changed in one RIS application within an exact date window (changed_from/changed_to), optionally including deletions (include_deleted) — the delta-sync and monitoring primitive for mirrors and watchers, and the only surface that reports removals. Unlike the search tools’ coarse, additive-only changed_since intervals, this is exact-dated and deletion-aware. application accepts every RIS application code listed by ris_list_reference topic applications, including BrKons, LrKons, Dsk, and BgblAuth. Each changed document comes back in a compact cross-class record — document_number (for ris_get_document), title, dates, binding_status, and rendition URLs — plus its last-changed date; removed documents come back as deleted records with a deletion timestamp. One application per call; page explicitly for large windows.

  ConnectorNo auth

• list_runtimesA

  MCPExplorerA

  List the runtimes generate_runtime_config supports (Claude Desktop, Cursor, VS Code, agent frameworks, …), with each one's config path. Enumerate these instead of guessing runtime slugs.

  ConnectorNo auth

• attach_analysisA

  jobctlA

  Attach a markdown company analysis (research you produced) to an application. Single document per application — a new call REPLACES the previous one. Max 100000 bytes (~100 KB) of utf-8. The user reads it in the dashboard, e.g. before an interview. Example: `attach_analysis({application_id: "…", markdown: "# Bosch\n\n## Culture…"})`.

  Connector

  Destructive

  No auth

• ic_spatial_beta_applyA

  Immersive CommonsA

  Submit an application to the 50-person spatial-computing beta. WRITES a real application under a real person's name and commits them to a 5-week in-person NDA-bound program, so CONFIRM EVERY ANSWER WITH YOUR HUMAN FIRST and never invent one on their behalf - particularly the NDA, commitment and in-person answers, which are promises they have to keep. Call ic_spatial_beta_program first for the catalog and the exact allowed values. One application per email address; a second is refused rather than silently merged. The response carries a `claim_token` shown EXACTLY ONCE: surface it to your human verbatim, because without it an applicant with no IC account can never read their own status again. No auth required; a token only attributes the application. Returns: { ok, application_id, claim_token, status, failed_gates, cohort, message }.

  ConnectorNo auth