Mixpanel MCP — wraps Mixpanel Data Export API (mixpanel.com/api)
Check an x402 endpoint before your agent pays it: avoid / caution / ok, proven on-chain.
Manage your family's calendars and lists in Cozi.
Publish and share access-controlled Markdown documents from any MCP-enabled AI tool.
Threat intelligence: enrich IOCs (IP, domain, URL, hash), search CVEs and actors, scan SBOMs
- Hello World: Returns a greeting with your account information
- Get Account Info: Returns information about the authenticated user, their organization, and subscription plan
- Get Scan Limits: Returns the remaining scan quotas for your organization (IP, domain, file, and crypto scans). Limits are per-day and shared across all organization members.
MLB Stats API MCP — official MLB statistics (keyless).
Provide structured access to Major League Baseball statistics through an MCP server.
- Get Stats
- Get Schedule: Get list of games for a given date/range and/or team/opponent.
- Get Player Stats: Returns a list of current season or career stat data for a given player.
Deterministic MLP tax engine with IRS citations.
Personal knowledge graph as an AI memory layer over MCP - read, save, and link your memories.
Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale
Self-hostable shared brain for you and your AI agents — docs, flows, meetings, decisions, rationale
- Search Docs: Searches docs in the current workspace by keyword, semantic similarity, or a hybrid of both. Use this when the user mentions a topic, term, or concept and you do not already know which do
- List Docs: Lists documents in the current workspace, ordered by most recently updated. Use this when: - The user asks "what docs do I have", "list my context", or similar - You need to discover what d
- Get Doc: Fetches the full markdown content and metadata of a single doc. Use this when: - You have a specific doc id or path from list_docs or search_docs - The user asks "show me X", "read X to me",
Hosted MCP memory and agent control plane for durable conversations, jobs, and operations.
Trust ratings for AI agents and websites.
- Claim Agent: Claim a verifiable identity — bind an agent to your organization so its trust and accountability record is provably yours. No human in the loop.
- Get Agent: Look up an agent's public identity and trust state by ID — the accountable record other agents and humans can rely on.
- Get Reputation: Look up an AI agent's published Trust Rating — Mnemom's portable reliability signal for autonomous software, computed from the agent's own verified activity record. Returns the rating
Trust infrastructure for AI agents: read a verifiable Trust Rating, claim an identity, earn a badge.
Bi-temporal memory-as-a-service and paid agent labor.
Knowledge commons for agent lessons, questions, and direct long-form peer discussions.
Persistent memory for AI agents - One memory.
- Memory Read: Recall relevant long-term memories via semantic search + Hebbian expansion. Returns ranked atoms with content, relevance, and concepts.
- Memory Stats: Report statistics about the caller's memory store (atom counts, Hebbian edges, domains, average valence/importance).
- Memory Write: Store a new long-term memory atom. The content is embedded, importance-gated, and linked via Hebbian associations. Returns whether it was stored and its atom_id.
An AI-first personal CRM you run in natural language: contacts, reminders, notes, and more.
Ephemeral no-signup demo of Mob, an AI-first personal CRM you run in natural language.
The design reference your AI agents are missing.
- Search Screens: Search Mobbin for UI screens using natural language. Returns screen images inline (as base64) along with metadata including image URLs, app names, and links to Mobbin.
Real mobile devices in the cloud for AI agents.
- Mobilenext List Available Devices: List your allocated devices and devices available for allocation on Mobile Next.
- Mobilenext Allocate Device: Reserve a device from the remote fleet. If you have a session ID, provide it to add the device to that existing session. If omitted, a new session is created automatically.
- Mobilenext Release Device: Release a device back to the remote fleet.
Control real Android and iOS devices with LLM agents — tap, swipe, type, automate flows.
Mobus is an MCP server for dataset discovery and research.
- Search Datasets: Search for datasets across multiple platforms (Kaggle, Hugging Face, data.gov, Zenodo, OpenML, UCI, Google, AWS, World Bank, WHO, NASA, Eurostat, Socrata, Papers with Code, Semantic S
- Get Dataset Details: Get detailed metadata for a specific dataset (columns, row count, files, popularity)
- Preview Dataset: Preview the first N rows of a dataset to inspect its data before downloading
High-performance, privacy-first image processing engine that bridges the gap between human intent and technical image manipulation.
- Squish: Compress, convert, resize, or transform an image from a public HTTPS URL. Returns the processed image inline. Defaults to JPEG output. Supports AVIF, JXL, WebP, PNG, and JPEG output formats. C
- Check Usage: Check how many image processing operations remain in the current billing period.
Mochii work graph: projects, tasks, meetings.
Remote MCP server for HTML-to-PDF and screenshots with OAuth and API-key auth.
Mock REST APIs, fake OAuth2/OIDC provider, uptime monitors + heartbeats, live badge/QR images.
Generate realistic relational test data — 156 field types, 22 locales, JSON/CSV/SQL, free previews.
MockHero generates realistic, relational synthetic test data from a JSON schema, plain-English prompt, or template — 156 field types, 22 locales, JSON/CSV/SQL…
- Estimate Agent Usage: Estimate MockHero agent-plan cost before generating data. No login or API key is required; include an API key only when you want the estimate to use actual daily usage.
- Create Agent Checkout: Create a loginless Polar Checkout URL for MockHero's metered agent plan. Polar is the Merchant of Record for checkout, tax collection, and remittance. The card payment step need
- Check Agent Checkout Status: Poll a Polar checkout created by create_agent_checkout using the returned claim_token.
Hosted MCP endpoint with realistic fake data for prototyping agents.
Missing a connector?
Tell us which service you need, or add your own MCP server: we will check it and publish it in the catalog.
Suggest a connector