Official
Read and write local files with configurable access controls.
filesystem, files, read, write
Best Agent-Friendly MCPs
MCPs designed with autonomous agents in mind: clear tool schemas, well-named actions, predictable failure modes, and tool descriptions that the model can understand without handholding. These are the servers that actually perform when you loop them inside Claude Code, Cursor Agent, or a custom agent harness.
51 MCPs in this collectionFilter:
agent-friendlyTop Agent-Friendly MCPs ranked
Popularity-ordered. Click any card for install snippets, fact sheet, and trust signals.
Current time and IANA timezone conversion — the first-party MCP that tells an agent what time it actually is.
time, timezone, clock, iana
Official
Persistent memory layer for AI agents — auto-summarised, cross-session recall.
memory, mem0, recall, personalization
Structured step-by-step reasoning for complex problem solving.
reasoning, thinking, agents, planning
Persistent knowledge graph memory across AI conversations.
memory, persistence, knowledge-graph, agents
Official
Full GitHub API access: repos, PRs, issues, and code search.
git, github, repos, prs
Official
Official Microsoft browser automation across Chromium, Firefox, and WebKit.
browser, automation, playwright, testing
Official
Run pre-built browser-automation Actors on managed infrastructure.
browser, automation, scraping, apify
Official
Google-published MCP server for databases — one Go binary speaks Postgres, MySQL, BigQuery, Spanner, AlloyDB, Snowflake, ClickHouse, MongoDB, Redis, and more.
database, multi-database, google, postgres
Official
AI-optimized web search with cleaned, citation-ready results.
search, web, research, rag
Up-to-date library docs pulled directly into your AI context.
coding, documentation, libraries, accuracy
Vision-first browser automation built for AI agents.
browser, automation, browser-use, vision
Official
Hosted, isolated Chromium runtime for AI agents that need a fresh browser per task.
browser, cloud, browserbase, automation
Official
AI-native browser automation: act, observe, and extract in plain English.
browser, stagehand, browserbase, ai-automation
Official
Open-source vector search with payload filtering, self-hostable or managed.
vector-db, qdrant, retrieval, embeddings
Official
Official Mapbox MCP — geocoding, directions, isochrones, search, and tiles across the Mapbox API surface.
mapbox, maps, geocoding, directions
Official
Official Salesforce MCP — SOQL queries, metadata deploy/retrieve, Apex tests, and org management from AI clients.
salesforce, crm, soql, apex
Full GitLab API access: repos, MRs, issues, pipelines, and registries.
git, gitlab, repos, mrs
Triage errors, inspect traces, and query events from Sentry.
sentry, errors, monitoring, observability
Local-first agent memory as plain Markdown — a semantic knowledge graph you and the agent can both read.
memory, markdown, knowledge-graph, obsidian
Official
Managed vector database for semantic search and retrieval in AI agents.
vector-db, pinecone, retrieval, embeddings
Real-time web search with privacy-focused results.
search, web, realtime, news
Open-source agentic browser automation that handles login walls and CAPTCHAs.
browser, agent, skyvern, vision
Read, create, and manage events across Google Calendar — via Google's official remote MCP or a self-hosted community server.
google-calendar, scheduling, events, productivity
AI-driven task management and decomposition for long-running agent projects.
agent, tasks, planning, persistence
Query webpages with structured natural language — selectors written for you.
scraping, agentql, extraction, queries
Supervisor-and-worker multi-agent coordination across coding CLIs — handoffs over MCP.
orchestration, multi-agent, handoff, aws-labs
Read and send Slack messages, manage channels and threads — the token-based community server, no admin approval needed.
slack, messaging, communication, automation
Read and post to Discord channels — community management for AI agents.
discord, chat, community, bot
Official
Embedded and hosted vector database for AI agents — open source, zero-ops.
vector-db, chroma, embeddings, retrieval
Read and create events in Apple Calendar via CalDAV from any MCP client.
calendar, apple, caldav, icloud
Official
Backlinks, keyword research, and rank tracking from the official Ahrefs remote MCP.
seo, backlinks, keywords, rank-tracking
Capture context and decisions across sessions — durable agent memory in markdown.
agent, memory, context, persistence
Official
Hosted Chromium with proxies and anti-bot evasion for AI agents.
browser, automation, hyperbrowser, proxies
Route one prompt across 300+ LLMs with a single API key.
ai, llm, openrouter, inference
Official
Official Cal.com hosted MCP — AI agents book, reschedule, and query availability across 34 tools via OAuth 2.1, no local install.
cal.com, scheduling, booking, calendar
Turn a vague goal into a dependency-tracked task graph an agent can execute step by step.
task-management, decomposition, planning, chain-of-thought
Official Foursquare Places MCP — POI search, GeoTagging, and rich place metadata across 100M+ places.
foursquare, places, poi-search, geocoding
Official Attio MCP — natural-language CRM control across records, lists, and notes via OAuth.
attio, crm, sales, pipeline
< 1 minLow
Pipedrive's own hosted MCP — search and update deals, contacts, organizations, leads, activities, and notes over OAuth.
pipedrive, crm, sales, pipeline
< 1 minLow
Full browser automation: navigate, click, screenshot, and scrape.
browser, automation, scraping, puppeteer
Search, inspect, and run Hugging Face models and datasets from an agent.
huggingface, ml, models, inference
Run any open-source model on Replicate from inside an AI agent.
ai, ml, replicate, inference
3 minLow
Archived
Secure cloud sandboxes for executing AI-generated code — npm MCP package archived; vendor recommends the hosted E2B platform.
coding, execution, sandbox, cloud
Official
Official HubSpot MCP server — CRM contacts, deals, and meeting scheduling from Claude or Cursor.
hubspot, crm, meetings, scheduling
10 minLow
Official
Official Fireflies remote MCP — query meeting transcripts, AI summaries, and action items via OAuth or API key.
fireflies, meeting-notes, transcripts, ai-summaries
2 minLow
Official
Official Fathom remote MCP — access meeting recordings, transcripts, summaries, and webhooks from any MCP client.
fathom, meeting-notes, transcripts, recordings
2 minLow
Vector database with first-class hybrid (vector + keyword) and modular embeddings (MCP server archived — package no longer published).
vector-db, weaviate, hybrid-search, retrieval
Archived
Multi-model orchestration — let Claude consult Gemini, GPT, and o-series as sub-agents. Upstream community repository archived; no further maintenance.
agent, orchestration, multi-model, consensus
Official
Anthropic-verified Fellow Connector — query meeting notes, transcripts, action items, and calendar events from Claude.
fellow, meeting-notes, transcripts, action-items
< 1 minLow
Official hosted MCP for booking-link scheduling — share availability without exposing the raw calendar.
calendar, scheduling, calendly, booking
5 minLow
FAQ: Agent-Friendly
What makes an MCP "agent-friendly"?
Three things: tool schemas that tell the model exactly what an argument is for, action names that match how agents describe intent ("create_issue" not "postIssueV2"), and errors that the model can recover from without a human in the loop.
Do non-agent-friendly MCPs still work with agents?
Usually yes, but they need more babysitting. A poorly-described tool may work for a human-in-the-loop chat but cause hallucinated argument values in an autonomous loop. For agents, prefer the ones on this page.
Are there any MCPs agents should avoid?
Action-taking MCPs without clear confirmation semantics are risky for agents — anything that can send an email, charge a card, or delete data should be carefully scoped. Check the auth model and capability-level filters before wiring into an autonomous loop.