Official
Read and write local files with configurable access controls.
filesystem, files, read, write
MCP Servers for Codex CLI
Codex CLI is OpenAI's terminal coding agent. It supports MCP through an `mcp_servers` section in its TOML config, letting you extend Codex with the same servers that power Claude Code, Cursor, and the rest of the ecosystem.
Set up MCP in Codex CLI
Four steps to connect your first MCP server.
- 1
Open ~/.codex/config.toml
First-run Codex creates the file at `~/.codex/config.toml` if it does not exist. Open it in your editor (or run `codex config edit`).
- 2
Add servers under [mcp_servers.*]
Each MCP gets its own subtable: `[mcp_servers.<name>]`. Inside, set `command` and `args` — the same shape used by every MCP install snippet on top-mcps.com, just in TOML.
- 3
Use env for secrets
Reference shell variables with `${VAR_NAME}` inside the `env = { ... }` table. Tokens stay in your shell environment, not in the committed config.
- 4
Restart Codex
Exit and relaunch the Codex CLI so it re-reads the config. Run `codex mcp list` to confirm the servers are connected and their tool counts are non-zero.
Config file locations
- User config
~/.codex/config.tomlCodex reads this on startup. Edit it directly or via `codex config`.
Example configjsonc
# ~/.codex/config.toml
[mcp_servers.filesystem]
command = "npx"
args = [
"-y",
"@modelcontextprotocol/server-filesystem",
"/Users/you/code",
]
[mcp_servers.context7]
command = "npx"
args = ["-y", "@upstash/context7-mcp"]
[mcp_servers.github]
command = "npx"
args = ["-y", "@github/github-mcp-server"]
env = { GITHUB_PERSONAL_ACCESS_TOKEN = "${GITHUB_TOKEN}" }Top MCPs for Codex CLI
The curated starting stack — install these first.
Official
Full GitHub API access: repos, PRs, issues, and code search.
git, github, repos, prs
Up-to-date library docs pulled directly into your AI context.
coding, documentation, libraries, accuracy
Archived
Anthropic's reference Postgres MCP — archived July 2025 and superseded by Postgres MCP Pro or the Supabase MCP.
database, sql, postgres, archived
Full browser automation: navigate, click, screenshot, and scrape.
browser, automation, scraping, puppeteer
Persistent knowledge graph memory across AI conversations.
memory, persistence, knowledge-graph, agents
All MCPs compatible with Codex CLI
101 servers verified to work with Codex CLI, ranked by popularity.
Official
Read and write local files with configurable access controls.
filesystem, files, read, write
Official
AI-optimized web search with cleaned, citation-ready results.
search, web, research, rag
Query and inspect MongoDB collections from Claude, Cursor, and VS Code.
database, nosql, mongodb, atlas
Inspect keys, run commands, and debug Redis from an AI agent.
database, cache, redis, valkey
Official
Run pre-built browser-automation Actors on managed infrastructure.
browser, automation, scraping, apify
Official
Embedded and hosted vector database for AI agents — open source, zero-ops.
vector-db, chroma, embeddings, retrieval
Official
Persistent memory layer for AI agents — auto-summarised, cross-session recall.
memory, mem0, recall, personalization
Inspect deployments, logs, and project state on Vercel from an AI agent.
vercel, hosting, deployment, nextjs
Local SQLite database access with full read/write support.
database, sqlite, local, storage
Retrieve web pages and convert them to clean markdown.
web, fetch, markdown, scraping
Official
Local Git operations: commit, diff, log, branch, and more.
git, local, commits, diff
Official
Full GitHub API access: repos, PRs, issues, and code search.
git, github, repos, prs
Archived
Anthropic's reference Postgres MCP — archived July 2025 and superseded by Postgres MCP Pro or the Supabase MCP.
database, sql, postgres, archived
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
Manage payments, customers, and subscriptions through Stripe.
stripe, payments, billing, commerce
Official
Official Microsoft browser automation across Chromium, Firefox, and WebKit.
browser, automation, playwright, testing
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
Managed vector database for semantic search and retrieval in AI agents.
vector-db, pinecone, retrieval, embeddings
Official
Manage Heroku apps, dynos, add-ons, and Postgres from an AI agent.
heroku, hosting, paas, postgres
Official
Manage Droplets, App Platform, Kubernetes, and Spaces from an AI agent.
digitalocean, hosting, cloud, kubernetes
Register and manage Name.com domains via the official MCP, auto-generated from their OpenAPI.
name-com, domains, registrar, dns
Send transactional and broadcast emails via the official Resend MCP.
resend, email, transactional, broadcast
Manage Mailgun messaging, domains, webhooks, and analytics from an AI agent.
mailgun, email, transactional, analytics
Official
Neural web search and page fetch for AI agents — official remote MCP at mcp.exa.ai/mcp.
exa, search, neural, retrieval
Official
Search, ask, research, and reason via the official Perplexity MCP.
perplexity, search, research, sonar
Official
Ad-free, high-quality web search and page-to-markdown extraction from an AI agent.
kagi, search, ad-free, extraction
Official
Scrape, crawl, extract structured data, and search the web from an AI agent.
firecrawl, scraping, crawl, extract
Official
Query ClickHouse and ClickHouse Cloud columnar warehouses from an AI agent.
database, warehouse, clickhouse, olap
Official
Search indices, inspect mappings, and run queries against Elasticsearch from an AI agent.
database, search, elasticsearch, elastic
Inject 1Password secrets into an AI agent's tool calls without exposing them in chat.
security, secrets, 1password, vault
Open-source SAST scanning against custom rules from an AI agent.
security, sast, semgrep, static-analysis
Inject secrets from Doppler into agent workflows without exposing values in chat.
security, secrets, doppler, credentials
Official
Send SMS, WhatsApp, and voice calls from an AI agent via Twilio.
communication, sms, whatsapp, voice
Official
Hosted Chromium with proxies and anti-bot evasion for AI agents.
browser, automation, hyperbrowser, proxies
Official
Manage Bitbucket Cloud repos, pipelines, and pull requests from an AI agent.
git, bitbucket, atlassian, pipelines
Official
Read channel messages, post replies, and trigger meetings from MS Teams.
communication, microsoft, teams, m365
Official
Inspect AWS resources, read CloudWatch logs, and audit IAM from an AI agent.
aws, cloud, cloudwatch, iam
Official
Read, write, and search across Notion pages, databases, and blocks.
notion, docs, databases, knowledge
Triage errors, inspect traces, and query events from Sentry.
sentry, errors, monitoring, observability
Official
Manage Workers, R2 buckets, DNS, and edge policies on Cloudflare.
cloudflare, edge, workers, dns
Official
Read products, orders, and inventory from your Shopify store.
shopify, ecommerce, products, orders
Official
Open-source vector search with payload filtering, self-hostable or managed.
vector-db, qdrant, retrieval, embeddings
Official
Browse, search, and Q&A across Box content from an AI agent — official remote MCP.
box, storage, enterprise, content
Official
Turn Make.com on-demand scenarios into agent-callable tools — official MCP.
make-com, automation, workflows, integromat
Official
Manage Jira, Confluence, and Compass via the official Atlassian Rovo MCP.
atlassian, jira, confluence, rovo
In-process analytical SQL over files and Parquet from an AI agent.
database, olap, duckdb, parquet
Full GitLab API access: repos, MRs, issues, pipelines, and registries.
git, gitlab, repos, mrs
Production-grade Postgres MCP with index advice, EXPLAIN, and health checks.
database, sql, postgres, performance
Archived
Search and read Google Drive files from an AI agent (archived reference implementation).
google-drive, storage, filesystem, documents
Official
Built-in MCP for Inngest functions, events, runs, and docs — zero auth, zero config.
inngest, events, workflows, dev-server
< 1 minLow
Run read-only MySQL queries and inspect schemas from an AI agent.
database, sql, mysql, mariadb
Fire IFTTT applets via webhooks from an AI agent. Community MCP wrapper archived; IFTTT itself is unaffected.
automation, webhooks, ifttt, integration
Send transactional email from an AI agent — verified deliverability, audit-friendly.
email, postmark, transactional, deliverability
Capture context and decisions across sessions — durable agent memory in markdown.
agent, memory, context, persistence
Official
Expose 8,000+ Zapier integrations as tools your AI agent can call.
zapier, automation, integrations, workflow
5 minLow
Real-time web search with privacy-focused results.
search, web, realtime, news
Full browser automation: navigate, click, screenshot, and scrape.
browser, automation, scraping, puppeteer
Up-to-date library docs pulled directly into your AI context.
coding, documentation, libraries, accuracy
Read and post to Discord channels — community management for AI agents.
discord, chat, community, bot
Search, inspect, and run Hugging Face models and datasets from an agent.
huggingface, ml, models, inference
Geocoding, place search, directions, and travel times from Google Maps.
maps, geocoding, places, directions
Real-time and forecast weather data via the OpenWeatherMap API.
weather, forecast, openweathermap, lifestyle
Read and write notes in your local Obsidian vault.
obsidian, notes, markdown, pkm
Inspect Figma designs, components, and variables from an agent.
figma, design, design-to-code, components
Query webpages with structured natural language — selectors written for you.
scraping, agentql, extraction, queries
Run any open-source model on Replicate from inside an AI agent.
ai, ml, replicate, inference
Route one prompt across 300+ LLMs with a single API key.
ai, llm, openrouter, inference
Personal task management with due dates — capture, schedule, and complete from chat. Community MCP package archived; Todoist itself is unaffected.
tasks, todoist, scheduling, reminders
AI-driven task management and decomposition for long-running agent projects.
agent, tasks, planning, persistence
Query Google BigQuery datasets from Claude, Cursor, and VS Code.
database, warehouse, bigquery, google-cloud
Archived
Scan code and dependencies for vulnerabilities from an AI coding assistant. Standalone MCP package archived; Snyk itself remains current via its IDE integrations.
security, vulnerabilities, sast, sca
Archived
Trigger and manage n8n workflows from an AI agent. Community MCP wrapper archived; n8n itself is unaffected.
automation, workflow, n8n, integration
Trigger Make scenarios and inspect runs from an AI agent.
automation, workflow, make, integromat
Open-source workflow automation — trigger and manage from an AI agent. Community MCP wrapper archived; Activepieces itself is unaffected.
automation, workflow, activepieces, open-source
Send messages and read channel history from a Telegram bot in an agent.
communication, messaging, telegram, bot
Self-hosted Slack alternative — read and post from an AI agent.
communication, chat, mattermost, self-hosted
Vision-first browser automation built for AI agents.
browser, automation, browser-use, vision
Self-hosted Git server — manage repos, issues, and PRs from an AI agent.
git, gitea, forgejo, codeberg
Send email and inspect deliverability via SendGrid from an AI agent.
email, sendgrid, transactional, deliverability
Archived
Secure cloud sandboxes for executing AI-generated code — npm MCP package archived; vendor recommends the hosted E2B platform.
coding, execution, sandbox, cloud
Official
Spin up Railway projects, services, and deploys via remote MCP with OAuth.
railway, hosting, deployment, paas
2 minLow
Official
2,800+ apps and managed OAuth via Pipedream's hosted MCP at mcp.pipedream.com.
pipedream, automation, workflows, oauth
Official
Cross-repo code search, navigation, and Deep Search via the official Sourcegraph MCP.
sourcegraph, code-search, navigation, deep-search
10 minMedium
Inspect schemas and run SQL against a Snowflake account from an AI agent.
database, warehouse, snowflake, sql
Read dynamic and static secrets from HashiCorp Vault inside agent workflows.
security, secrets, vault, hashicorp
Enterprise iPaaS — trigger Workato recipes from an AI agent.
automation, workflow, workato, ipaas
Full Supabase access: database, auth, storage, and edge functions.
supabase, database, backend, postgres
Read and send Slack messages, manage channels and threads.
slack, messaging, communication, automation
Manage Linear issues, projects, and cycles from AI context.
linear, project-management, issues, productivity
Read, create, and manage events across Google Calendar.
google-calendar, scheduling, events, productivity
Vector database with first-class hybrid (vector + keyword) and modular embeddings (MCP server archived — package no longer published).
vector-db, weaviate, hybrid-search, retrieval
Open-source scheduling — booking pages, availability, and event types for AI agents. MCP wrapper is archived; the Cal.com platform itself remains current.
calendar, scheduling, cal-com, booking
Booking-link scheduling — share availability without exposing the raw calendar.
calendar, scheduling, calendly, booking
Read and create events in Apple Calendar via CalDAV from any MCP client.
calendar, apple, caldav, icloud
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
Archived
Deploy and manage Render web services, static sites, cron jobs, and Postgres from an AI agent. Official MCP server is archived; Render platform is unaffected.
render, hosting, deployment, paas
Archived
Manage Porkbun domains, DNS, DNSSEC, and SSL — read-only by default. Community MCP repository archived; Porkbun itself is unaffected.
porkbun, domains, registrar, dns
Send, read, search, and label Gmail from an AI agent — community MCP with auto-OAuth.
gmail, email, community, google
Open-source agentic browser automation that handles login walls and CAPTCHAs.
browser, agent, skyvern, vision
FAQ: MCP in Codex CLI
Where does Codex CLI store its MCP config?
At `~/.codex/config.toml`. The entire config is a single TOML file, with MCP servers living under `[mcp_servers.<name>]` subtables. There is no per-project config today — Codex uses the same config across every repo.
How is the config different from Claude Desktop or Cursor?
Shape-wise it is the same — `command`, `args`, optional `env` — but the format is TOML instead of JSON, and keys use `[mcp_servers.<name>]` subtables instead of the `{"mcpServers": {...}}` nesting you see in JSON clients.
Can I share MCP config across my team in Codex?
Only indirectly today. Codex uses a single user-level config, so team sharing is typically done by committing a template `config.toml` to your repo and asking teammates to copy the `[mcp_servers.*]` blocks they want into their own Codex config.
Does Codex CLI support env var interpolation?
Yes. Inside the `env = { ... }` inline table you can reference `${VAR_NAME}` and Codex resolves it from the shell at launch. That lets you keep tokens out of the committed config while still passing them to the MCP process.
Why does Codex call them "mcp_servers" (plural) and not "mcpServers"?
TOML convention. Codex's config is snake_case throughout, and `mcp_servers` matches the style of its other subtables (`model`, `tools`, `projects`). The underlying MCP protocol is unchanged — only the config-file shape differs.
Browse every MCP server → top-mcps.com