Current time and IANA timezone conversion — the first-party MCP that tells an agent what time it actually is.
- Home
- Collections
- Best Read-Only MCPs
Best Read-Only MCPs
Read-only MCPs can inspect, query, and fetch — but they never write, post, or trigger side effects. That makes them the safest option for exploratory agent workflows, production databases, and anywhere a misfire would cost money or corrupt state.
read-onlyTop Read-Only MCPs ranked
Popularity-ordered. Click any card for install snippets, fact sheet, and trust signals.
Retrieve web pages and convert them to clean markdown.
Look up Terraform Registry providers and modules, and manage HCP Terraform workspaces from an AI agent.
Query and inspect MongoDB collections from Claude, Cursor, and VS Code.
Up-to-date library docs pulled directly into your AI context.
Inspect keys, run commands, and debug Redis from an AI agent.
Query ClickHouse and ClickHouse Cloud columnar warehouses from an AI agent.
Manage Bitbucket Cloud repos, pipelines, and pull requests from an AI agent.
Query Google Ads campaigns, metrics, and account performance with GAQL — Google's official MCP.
Inspect Figma designs, components, and variables from an agent — the widely adopted community server.
Search indices, inspect mappings, and run queries against Elasticsearch from an AI agent.
Official Mapbox MCP — geocoding, directions, isochrones, search, and tiles across the Mapbox API surface.
Triage errors, inspect traces, and query events from Sentry.
Live SERP, keyword, backlink, and on-page SEO data for an AI agent.
Query GA4 reports, funnels, and realtime data from an AI agent.
Score npm, PyPI, Go, and Maven dependencies for supply-chain and vulnerability risk before an agent installs them.
Real-time web search with privacy-focused results.
Run read-only MySQL queries and inspect schemas from an AI agent.
Official Plaid MCP — developer sandbox tooling and dashboard diagnostics, not a live bank-data connector.
Geocoding, place search, directions, and travel times from Google Maps.
Inject secrets from Doppler into agent workflows without exposing values in chat.
Query Search Console clicks, impressions, and queries from an AI agent.
Anthropic's reference Postgres MCP — archived July 2025 and superseded by Postgres MCP Pro or the Supabase MCP.
Inspect deployments, logs, and project state on Vercel from an AI agent.
Search and read Google Drive files from an AI agent (archived reference implementation).
Inject 1Password secrets into an AI agent's tool calls without exposing them in chat.
Official Foursquare Places MCP — POI search, GeoTagging, and rich place metadata across 100M+ places.
Search, inspect, and run Hugging Face models and datasets from an agent.
Self-hosted Git server — manage repos, issues, and PRs from an AI agent.
Official Fireflies remote MCP — query meeting transcripts, AI summaries, and action items via OAuth or API key.
Official Fathom remote MCP — access meeting recordings, transcripts, summaries, and webhooks from any MCP client.
Manage Porkbun domains, DNS, DNSSEC, and SSL — read-only by default. Community MCP repository archived; Porkbun itself is unaffected.
Anthropic-verified Fellow Connector — query meeting notes, transcripts, action items, and calendar events from Claude.
Inspect schemas and run SQL against a Snowflake account from an AI agent.
Real-time and forecast weather data via the OpenWeatherMap API.
FAQ: Read-Only
Why use a read-only MCP specifically?
Agents will sometimes call tools you didn't expect. For a production database or a paid API, you want the server itself to refuse mutations — not just your prompt asking it nicely. Read-only is a hard stop, not a soft hint.
Can I make any MCP read-only?
Partially. Many MCPs gate writes behind environment variables or credentials scopes. If the MCP exposes write tools but you hand it read-only credentials, the write calls will fail at the API layer — same outcome in practice.

