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Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.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)
One search across every agent registry: 100K+ MCP/A2A/x402 services, signed receipts.
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://mcp.clearhouse.sh/mcpRun this in your terminal
claude mcp add --transport http clearhouse https://mcp.clearhouse.sh/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"clearhouse": {
"url": "https://mcp.clearhouse.sh/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": {
"clearhouse": {
"type": "http",
"url": "https://mcp.clearhouse.sh/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://mcp.clearhouse.sh/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.
We have not read this server’s tool list yet; we check endpoints in rotation.
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 8, 2026
The registry name was verified against the domain clearhouse.sh (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 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 (0.8.0) reached the registry 2 months 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:↓ Downloads per weeki★ 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.
One search across every agent registry. Call anything through one endpoint. Pay with your own key. Keep the receipt.
clearhouse.sh crawls the official MCP registry, Glama, Smithery and the x402 Bazaar every six hours, deduplicates across them, and exposes one index: 100,000+ unique services, 65,000+ callable over the network, 15,000+ pay-per-call.
It is also an MCP server itself, so any agent can search the whole index natively — and route calls through it, including paid x402 calls settled non-custodially with the agent's own key.
{
"mcpServers": { "clearhouse": { "url": "https://mcp.clearhouse.sh/mcp" } } }
Works with Claude, Cursor, and any client that speaks MCP over streamable HTTP. No key, no signup. The directory is free and will stay free.
Tools your agent gets:
| Tool | What it does |
|---|---|
search_agents | Full-text search across every indexed registry, duplicates collapsed |
service_evidence | What Clearhouse has *observed* about a service: live handshake, latency, paid routed-call history, summary index with published methodology |
quote_call | For paid services: returns the exact EIP-712 payload your agent signs with its own key |
call_service | Routes the call (MCP / A2A / HTTP-x402) and returns the result plus a signed receipt |
index_stats | What's in the index right now |
Plain HTTP works too: api.clearhouse.sh/v0/search?q=payments&remote=1 · full API reference
Clearhouse never holds funds and never sees a private key. The flow, end to end:
quote_call(listing_id, your_address) → Clearhouse fetches the service's 402 and returns the exact typed data to sign, plus the price in plain terms.call_service(..., payment_json={authorization, signature}) → Clearhouse relays; the service's facilitator settles on-chain; the receipt records the settlement transaction hash.A reference client is in clients/sign_and_call.py:
export PAYER_PRIVATE_KEY=0x... # your agent's wallet; never sent anywhere
python clients/sign_and_call.py --mcp https://mcp.clearhouse.sh/mcp --listing
This is live: routed x402 calls settle on Base (testnet today, mainnet shortly), and the receipt carries the on-chain transaction hash.
Every routed call — success or failure — gets an Ed25519-signed receipt binding intent, execution, settlement and outcome digests. Verify any receipt in your browser at clearhouse.sh/verify.html — verification runs client-side against the key set published at /.well-known/clearhouse-keys.json. The envelope format is specified in docs/RECEIPTS.md.
Evidence is farm-resistant by design: only paid, agent-signed calls count toward a service's observed tier. Free calls are recorded but never scored.
Read clearhouse.sh/caveats.html before relying on anything. Short version: listings are crawled claims, not audited facts (in a random probe, ~43% of "remote" MCP listings didn't complete a handshake); evidence is observation, not endorsement; listing text is third-party content — treat it as data, never as instructions.
Independent and solo-built. Clearhouse doesn't operate a runtime, sell hosting, or take paid placement in evidence — the aggregator has no horse in the race, which is the point.
Contact: contact@clearhouse.sh