"OpenAI" matching MCP tools:

• searchA

  ConferenceGridA

  Compatibility tool: OpenAI connectors require a tool with this exact name and one string argument. Searches conferences by free text — a city, a topic, a company or a conference name — and returns at most 10 results as id, title and url only. If you can pass separate arguments, use search_conferences instead: city, country, topic and dates, up to 100 rows, with the detail this one leaves out. Pass an id to `fetch`.

  ConnectorOAuth

• get_available_modelsA

  Gonka Second Opinion (multi-model)A

  List all AI models available on Gonka Network with live pricing. Models work as drop-in replacements for OpenAI and Anthropic — same SDK, same API calls. Use this when user asks which model to use or wants alternatives to GPT-4o / Claude. Returns: model IDs (use directly in openai.chat.completions.create), status, USD per 1M tokens. After this: call calculate_savings() to see annual savings with these models.

  ConnectorNo auth

• secret_scanA

  IA-QA — 130+ QA & Dev Tools for AI AgentsB

  Scan text or code for leaked secrets: API keys (AWS, GCP, Azure, OpenAI, Anthropic, Stripe, GitHub, GitLab, Slack, Twilio, SendGrid, HuggingFace), private keys (RSA/EC/PGP), JWTs, database connection strings, Bearer tokens, and Basic auth headers. Returns a list of findings with type, severity, line number, and a redacted preview. Use before committing code, sharing logs, or sending text to an LLM. 100% regex-based, zero network calls.

  ConnectorNo auth

• synap_chat_completionA

  SynapA

  Send a conversation to a model on Synap, Linkrra's OpenAI-compatible inference API, and get the model's reply. Use this when you need text generated, code written or a question answered by one of the open models Synap serves. This is the only tool here that costs money: it bills prompt and completion tokens to the Synap API key supplied as the Authorization: Bearer header on the MCP connection. With no key it returns an error and nothing is spent; a key with no balance returns insufficient_credits. Call synap_estimate_cost first if the price matters. Returns the standard OpenAI chat.completion JSON (choices[0].message.content holds the reply, usage holds token counts). The call is not streamed and keeps no memory between calls — send the full message history each time.

  ConnectorNo auth

• check_viewA

  QuillmA

  Test-renders a view in a real headless browser, reviews it, and reports render errors, console errors, which datasets it loaded, and what a reader would still be missing. The review sends a screenshot and the page's text to OpenAI, unless the workspace turned checks off. Set screenshot=true to also get an image so you can judge the layout yourself. create_view and update_view already run this automatically; use this tool when you want the screenshot, after changing a dataset, or to confirm the review is clean before you tell the user it is done.

  ConnectorOAuth

• get_pricingA

  Gonka Second Opinion (multi-model)A

  Get live Gonka Network pricing — cheap alternative to OpenAI and Anthropic APIs. Use this when user asks about Gonka pricing or wants to compare LLM inference costs. Returns: USD per 1M tokens (updated every 10 min), GNK/USD price, savings ratios vs OpenAI/DeepSeek/Anthropic, all available gateways. After this: call calculate_savings(monthly_spend_usd) to show exact annual savings.

  ConnectorNo auth

• llm_chatA

  agentdata-nlA

  LLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.

  ConnectorNo auth

• start_visibility_checkA

  Asked ThriceA

  Measure whether a brand shows up when buyers ask AI assistants for a recommendation. Asks real buyer questions to OpenAI, Anthropic and Gemini and reports what they answered, not what they claim they would answer. Free, no signup, one measurement per domain every 30 days. Returns a runId: call get_visibility_check with it after about a minute. If the domain was already measured this month the response says quota_reached and includes when it ran.

  ConnectorNo auth

• start_visibility_checkA

  LLM AuditA

  Measure whether a brand shows up when buyers ask AI assistants for a recommendation. Asks real buyer questions to OpenAI, Anthropic and Gemini and reports what they answered, not what they claim they would answer. Free, no signup, one measurement per domain every 30 days. Returns a runId: call get_visibility_check with it after about a minute. If the domain was already measured this month the response says quota_reached and includes when it ran.

  ConnectorNo auth

• create_projectA

  MockbirdA

  Create a new mock REST API project. Returns {id, adminKey, baseUrl, resources[]}. SAVE the adminKey — it is required for admin operations (add_resource, custom_route, snapshots) and is shown only once. Presets seed a full backend: blog (posts/comments/authors), ecommerce (products/orders/customers/reviews), saas (users/teams/events), payments (Stripe-shaped sandbox: charges/refunds/subscriptions/customers + payment_intent create→confirm flow + /v1/balance — no keys), openai (ready OpenAI-compatible mock — chat completions incl. streaming SSE, embeddings with a real 1536-dim vector, models; point OPENAI_BASE_URL at {baseUrl}/v1). Omit preset for a starter project (one seeded "items" resource — live data immediately, reshape or delete it); use "blank" for a truly empty project you fill via add_resource or import_data. The mock API is then live at baseUrl: standard REST CRUD (GET/POST/PUT/PATCH/DELETE), CORS enabled, no auth needed. Every project also serves a mock OAuth2/OIDC provider at {baseUrl}/.well-known/openid-configuration (PKCE code flow, client_credentials, RS256 JWKS — any client_id works) for testing auth flows.

  ConnectorNo auth

• fetchA

  ConferenceGridA

  Compatibility tool: OpenAI connectors require a tool with this exact name and one string argument. Returns one conference for an id from `search` — dates, location, speakers, sponsors and exhibitors — as a block of text. Prefer get_conference where you can: it returns the same edition as structured fields and lets you set how many of each list come back. The id is the conference slug.

  ConnectorOAuth

• check_serverA

  protogridA

  Probe a remote MCP server URL once, credential-free and without calling its tools, and get its quality checks and its readiness for the Claude and OpenAI directories. Pass `url` to start a check (waits up to 25 s for the result), or `id` to read one. Quota: a few checks per hour anonymously, more with an API key.

  ConnectorNo auth

• search_official_docsA

  404.directoryA

  Search current first-party OpenAI, Microsoft Learn, AWS, and Cloudflare documentation in one call. Use this as the default documentation research tool for questions involving any of those providers, especially comparisons or cross-cloud architecture. Select only relevant sources when the provider is known; omit sources to search all four in parallel. Returns each provider result separately with partial-failure reporting and provenance. No account or API key is required.

  ConnectorNo auth

• get_agent_opportunitiesA

  TensorFeedA

  Get TensorFeed's daily scan of new repositories across the AI agent ecosystem (Anthropic, OpenAI, Microsoft, ModelContextProtocol, HuggingFace, LangChain, frontier labs) plus recent MCP/x402/skills keyword sweeps. Each opportunity includes the GitHub repo path, description, stars, last update, the source signal, and a composite score (signal weight × log10(stars+1) × recency decay). Refreshed daily at 13:30 UTC. Useful for surfacing distribution targets, integration ideas, or just a daily digest of what's launching across the agent space. License: GitHub data via the public Search API; output is TensorFeed's curated ranking.

  ConnectorNo auth

• buy_phone_numberA

  agentdata-nlA

  Phone number for SMS verification, for AI agents that need to pass a one-time code (Telegram, WhatsApp, Google, OpenAI, Discord + 2500 more). You pay only when a real code arrives — no code, no charge. Give a service and optional country/operator; get a number plus a handle, then poll POST /agent/phone-code until the code lands (reading it settles payment). Dynamic price per request (in the 402), USDC via x402, no account or KYC. Lawful one-time verification only.

  ConnectorNo auth

• count_tokensA

  inktomd MCP ServerA

  Count the exact number of tokens in a text string for a specific AI model. Uses tiktoken for OpenAI models and estimates for others. Args: text: The text to count tokens for model: The AI model to count tokens for. Options: gpt-4o, gpt-4o-mini, gpt-4.1, claude-sonnet, claude-haiku, gemini-pro, gemini-flash, llama-4, deepseek-v3, mistral-large. Default: gpt-4o Returns: Token count information including count, context window, and fit status

  ConnectorNo auth

• get_model_historyA

  inferenceindexer-mcpA

  Get HISTORICAL price data / trends for one model. This is InferenceIndexer's differentiator: aggregators like OpenRouter expose only current price; this returns the price over time (input, output, blended $/M), enabling trend analysis. Args: model_id: Canonical model id, e.g. 'openai/gpt-5.6'. days: History window in days (1-365, default 30; plan-dependent). Returns: historical price series for the model.

  ConnectorNo auth

• fetchA

  IBGE Brasil MCPA

  Returns the full document for an id obtained from `search`, as { id, title, text, url, metadata }: `text` is the readable content (Markdown) and `url` the canonical public page to cite. Companion of `search` in the OpenAI Deep Research contract, over the IBGE (Brazilian official statistics: SIDRA tables, municipalities, known indicators) catalog. Only ids returned by `search` are valid; an unknown id returns an error. The `ibge_*` tools (`ibge_sidra`, `ibge_cidades`, `ibge_indicadores`, `ibge_comparar`…) remain the tools for data queries. Behavior: read-only and idempotent — a live GET against the public source when the document needs it.

  ConnectorNo auth

• spendline_list_providersA

  SpendlineA

  Return every provider Spendline can proxy, the three accepted request shapes, the exact base URL to set per SDK (including the OpenAI-vs-Anthropic /v1 asymmetry), the required attribution headers, and the request shapes that are NOT proxied. Resolve routing from here instead of hardcoding it.

  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: a per-search charge for each of `web_search_calls` plus the model's own token cost (fresh input = `input_tokens − cached`). 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

• get_crawler_accessA

  found-by-ai-monitorA

  Whether this business's robots.txt allows or blocks each documented AI crawler: OpenAI, Anthropic, Google, Perplexity, Apple, Microsoft, Meta and Common Crawl, split by what each one is for (search, model training, or fetching a page because a user asked). Read from the stored evidence of the latest deep scan, with the matching robots.txt rule quoted for each. Also names vendors this checker cannot assess, so an agent does not read silence as permission.

  ConnectorNo auth