Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Search a curated directory of 800+ AI agents, MCP servers, and agentic tools.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://agentswitchboard.dev/api/mcpRun this in your terminal
claude mcp add --transport http agentswitchboard https://agentswitchboard.dev/api/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agentswitchboard": {
"url": "https://agentswitchboard.dev/api/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"agentswitchboard": {
"type": "http",
"url": "https://agentswitchboard.dev/api/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://agentswitchboard.dev/api/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
search_agentsSearch the curated Agent Switchboard directory of AI agents, MCP servers, and agentic tools. Filter by task, category slug, access methods, official (first-party listings from major vendors), verified, and/or auth type; sort by relevance, newest, most skills, or name. Verified: w
get_agentFull detail for one agent by slug: skills, auth, streaming/push support, tags, provider links, and useItNow: how to start using it (MCP client config, install command, API base URL, setup links). Verified: we checked it works — its URLs load and its declared access (API, MCP, CLI
list_categoriesAll directory categories with live agent counts. Slugs are valid inputs for search_agents.
compare_agentsPut 2 or 3 listings side by side, as the site's /compare page does. For each listing: the facts that set it apart from the others ("Only one with a CLI", "No auth required", "Most skills (12)"). Then one row per field, with each listing's value by slug: what it is, provider, offi
alternatives_toListings that could stand in for one listing, strongest first, as on its /agents/ /alternatives page. Each alternative is in the listing's main category, offers at least one of its access methods, and overlaps on what it does (shared skills and tags, rarer ones counting for more)
connect_bundleOne MCP client config to paste ({"mcpServers": …}, as Cursor and other MCP clients read it) for up to 10 listings, and how each one connects. A listing is in the config when its own docs give a hosted server address or a local command. An MCP server whose docs give neither comes
submit_listingSuggest a new listing for the Agent Switchboard directory. This opens a PUBLIC GitHub issue that the maintainer reviews by hand; it does not publish anything. Use it only when the user asks to submit or list a product, after you show them the name, URL, and description you will s
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account assafbar2, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 654 ms (HTTP 200)
No sign-in needed
Read 7 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.2.0) reached the registry 7 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
The curated directory for the agentic web — AI agents, MCP servers, and agentic tools with real API, MCP, CLI, or browser-extension access. Live at [agentswitchboard.dev](https://agentswitchboard.dev).
A listing marked Verified is one we checked works: its URLs load and its declared access (API, MCP, CLI or extension) responds. Re-checked monthly; the label drops if it stops working.
Point any MCP client at it and query the catalog with native tools:
{
"mcpServers": { "agentswitchboard": { "url": "https://agentswitchboard.dev/api/mcp" } } }
Tools: search_agents · get_agent · list_categories · compare_agents · alternatives_to · connect_bundle (one MCP client config for up to 10 listings) · submit_listing (files a public GitHub issue for review; publishes nothing). Streamable HTTP, no auth. Stdio-only clients: npx -y mcp-remote https://agentswitchboard.dev/api/mcp
Setup for Grok, Grok Bot, the xAI API, Claude, and ChatGPT: agentswitchboard.dev/connect.
Prefer plain HTTP? There's a REST search too:
curl "https://agentswitchboard.dev/api/agents?q=video&access=mcp&limit=5"
curl "https://agentswitchboard.dev/api/agents/agentmail" curl "https://agentswitchboard.dev/api/categories" curl "https://agentswitchboard.dev/api/compare?a=deepgram&b=assemblyai" curl "https://agentswitchboard.dev/api/bundle?items=linear,sentry-mcp,playwright-mcp"
OpenAPI: /openapi.json. Connector skill: /skill.md.
Also machine-readable: /agents.json (full catalog, CORS-open), in-browser tools via WebMCP (document.modelContext), and an agent-optimized view on every page (the "For Agents" toggle).
Full API reference: [docs/API.md](docs/API.md) — REST search/detail/categories, compare, alternatives and the connect bundle, MCP, WebMCP, and the catalog dump.
The entire catalog lives in this repo:
content/
agents/ .json one file per agent — the source of truth categories.json category definitions changelog.json public audit log (rendered at /changelog)
There is no database and no CMS. Editing content = editing files. Merging to main = publishing. Every entry is schema-validated in CI (scripts/validate-content.ts) — a bad entry cannot merge. A weekly job link-checks every listing's agent and provider URLs.
Want to add or fix a listing? See [CONTRIBUTING.md](CONTRIBUTING.md). Non-developers: agentswitchboard.dev/submit.
npm install
npm run dev # no env vars needed — content is right here
| Command | |
|---|---|
npm run dev | dev server |
npm run build | production build (SSG, all pages) |
npm test | unit tests |
npm run lint / npm run typecheck | quality gates |
npx tsx scripts/validate-content.ts | validate the catalog |
npx tsx scripts/check-links.ts | link-rot sweep |
npx tsx scripts/cms.ts | content ops: find / feature / update / unpublish |
npx tsx scripts/weekly-drop.ts | batch-add agents (see file header) |
npx tsx scripts/drop-impact.ts | what a content change does elsewhere on the site, compared with origin/main |
Stack: Next.js (App Router) · Tailwind · file-based catalog · deployed on Vercel.
app/, components/, lib/, scripts/, config) — MITcontent/, including every content/agents/*.json listing, and the same data at /agents.json, the REST API and the MCP server) — CC BY-NC 4.0: reuse for non-commercial purposes with attribution to Agent Switchboard; contact us for commercial use. Submitted listings are contributed under CC BY-NC 4.0. (Versions up to 2026-09-25 remain CC BY 4.0.)