MCP Server & Agent-Skill Registry API API
The MCP Server & Agent-Skill Registry API helps you discover and vet MCP servers and agent skills as clean JSON.
🤖 Using an AI assistant? Copy this link into ChatGPT / Claude / Cursor — it reads every endpoint and parameter instantly and tells you if this API fits your use case.
The primary search endpoint returns servers and skills with id, name, type, description, GitHub URL, license, version, transport, status and cross-registry sources, and you can pull a server or skill detail, security_signals, trending entries and the list of sources. It is built for AI-agent platforms and developer tools that need a searchable, security-aware index of the MCP ecosystem. One ReefAPI key, one shared credit pool, the standard envelope.
Real request and response JSON
Captured from the indexed primary action, search, on .
{
"method": "POST",
"url": "https://api.reefapi.com/mcp-registry/v1/search",
"headers": {
"x-api-key": "$REEF_KEY",
"content-type": "application/json"
},
"body": {
"query": "filesystem",
"limit": 10
}
}{
"ok": true,
"meta": {
"api": "mcp-registry",
"endpoint": "search",
"mode": "live",
"latency_ms": 1953.6,
"record_count": 10,
"bytes": 0,
"cache_hit": false,
"completeness_pct": 100
},
"data": {
"query": "filesystem",
"type": "mcp",
"results": [
{
"id": "smithery:googledrive",
"name": "[redacted-name]",
"title": "Google Drive",
"type": "mcp",
"description": "Upload, organize, and share files in the cloud. Manage folders, set permissions, and search across stored documents.",
"github_url": null,
"license": null,
"version": null,
"transport": [
"http"
],
"status": null,
"updated_at": "[redacted-phone]T07:26:50.147Z",
"sources": [
"smithery"
],
"cross_registry_count": 1,
"source_urls": {
"smithery": "https://smithery.ai/servers/googledrive"
},
"metrics": {
"use_count": 15651,
"verified": true,
"score": 0.02857142857142857
}
},
{
"id": "smithery:one_drive",
"name": "[redacted-name]",
"title": "One drive",
"type": "mcp",
"description": "OneDrive is Microsoft’s cloud storage solution enabling users to store, sync, and share files across devices, offering offline access, real-time collaboration, and enterprise-grade security",
"github_url": null,
"license": null,
"version": null,
"transport": [
"http"
],
"status": null,
"updated_at": "[redacted-phone]T12:47:26.816Z",
"sources": [
"smithery"
],
"cross_registry_count": 1,
"source_urls": {
"smithery": "https://smithery.ai/servers/one_drive"
},
"metrics": {
"use_count": 1082,
"verified": true,
"score": 0.02564102564102564
}
},
{
"id": "smithery:dropbox",
"name": "Dropbox",
"title": "Dropbox",
"type": "mcp",
"description": "Store, sync, and share files across devices. Manage folders, control access permissions, and collaborate on documents.",
"github_url": null,
"license": null,
"version": null,
"transport": [
"http"
],
"status": null,
"updated_at": "[redacted-phone]T12:48:17.645Z",
"sources": [
"smithery"
],
"cross_registry_count": 1,
"source_urls": {
"smithery": "https://smithery.ai/servers/dropbox"
},
"metrics": {
"use_count": 274,
"verified": true,
"score": 0.027777777777777776
}
}
],
"total": 10,
"source_health": {
"official": "ok",
"glama": "ok",
"smithery": "ok"
}
}
}What the MCP Server & Agent-Skill Registry API API does
| Action | Description | Concrete use case | Key params |
|---|---|---|---|
| search | Normalized cross-registry search over the Official MCP Registry, Glama and Smithery (and skills via GitHub). Dedups the same server across registries by canonical GitHub repo and returns cross-registry presence. | Ops teams call search to get normalized cross-registry search over the Official MCP Registry, Glama and Smithery (and skil…. | query, type, source, sort, limit |
| server_detail | Full merged profile for one MCP server across every registry it appears in: manifest (tools/capabilities/transport), install paths (packages/remotes/connections), license, GitHub repo health, and cross-registry presence (how many registries list it = trust signal). | Developer tools call server_detail to get full merged profile for one MCP server across every registry it appears in. | id, repo_health |
| skill_detail | Metadata for one agent-skill repo (GitHub-backed). Fetches the repo + its SKILL.md frontmatter (name/description/license) + repo health. | Validation workflows call skill_detail to get metadata for one agent-skill repo (GitHub-backed). | id |
| security_signals | HEURISTIC risk signals for an MCP server (NOT a safe/unsafe certification). Flags permission breadth (fs/network/exec), credential/env-var requests, repo health (archived/low-adoption), prompt-injection patterns in description/manifest, and corroboration (cross-registry presence). Always returns a disclaimer. | Data-quality teams call security_signals to get hEURISTIC risk signals for an MCP server (NOT a safe/unsafe certification). | id |
| trending | New / rising entries. MCP: most-used servers on Smithery + latest on the Official registry. Skills: recently-created GitHub skill repos. | Ops teams call trending to get new / rising entries. | type, limit |
| list_sources | The registries this engine aggregates, their roles, auth status and live reachability. Free. | Developer tools call list_sources to get the registries this engine aggregates, their roles, auth status and live reachability. | none |
Call search from your stack
curl -X POST https://api.reefapi.com/mcp-registry/v1/search \
-H "x-api-key: $REEF_KEY" \
-H "content-type: application/json" \
-d '{"query":"filesystem","limit":10}'import requests
r = requests.post(
"https://api.reefapi.com/mcp-registry/v1/search",
headers={"x-api-key": REEF_KEY},
json={
"query": "filesystem",
"limit": 10
},
)
print(r.json()["data"])const res = await fetch("https://api.reefapi.com/mcp-registry/v1/search", {
method: "POST",
headers: {
"x-api-key": process.env.REEF_KEY,
"content-type": "application/json",
},
body: JSON.stringify({
"query": "filesystem",
"limit": 10
}),
});
const { ok, data, meta, error } = await res.json();Ask your MCP-connected assistant: call reefapi.mcp-registry.search with {"query":"filesystem","limit":10}.Who uses this API and why
- AI-agent platforms call search to let users discover MCP servers by capability and transport.
- Security-conscious teams use security_signals to vet an MCP server before connecting it.
- Developer tools use trending and server_detail to surface and compare popular MCP servers.
Questions developers ask before integrating
What is the MCP Server & Agent-Skill Registry API API?
MCP Server & Agent-Skill Registry API API is a ReefAPI endpoint group for mcp server & agent-skill registry api It returns live JSON through POST requests under /mcp-registry/v1.
Is the MCP Server & Agent-Skill Registry API API free to try?
Yes. ReefAPI starts with 1,000 free credits, no card required. MCP Server & Agent-Skill Registry API calls use the same shared credit balance as every other ReefAPI engine.
Do I need a MCP Server & Agent-Skill Registry API login or account?
No login to MCP Server & Agent-Skill Registry API is needed for the API response. You call ReefAPI with your x-api-key header, and the playground can run live examples before you create a production key.
How fresh is the MCP Server & Agent-Skill Registry API data?
The page example is captured from a live search call, and production requests fetch live data through ReefAPI rather than a static sample.
How many credits does the MCP Server & Agent-Skill Registry API API use?
MCP Server & Agent-Skill Registry API actions currently cost 1-2 credits per successful call. Failed or blocked calls are free, and all APIs draw from one credit pool.
Can I call MCP Server & Agent-Skill Registry API from an AI assistant or MCP client?
Yes. Connect ReefAPI once through MCP and your assistant can call mcp-registry actions with the same key, credit pool and JSON envelope used by normal REST requests.
Is the MCP Server & Agent-Skill Registry API API a MCP Server & Agent-Skill Registry API scraper?
It is the managed alternative to a DIY MCP Server & Agent-Skill Registry API scraper. Instead of building and maintaining your own scraper — proxies, headless browsers, captcha and constant breakage — you call one ReefAPI endpoint and get the same mcp server & agent-skill registry api back as clean JSON.
Why does my MCP Server & Agent-Skill Registry API scraper keep getting blocked?
Most MCP Server & Agent-Skill Registry API scrapers break on anti-bot defenses, rate limits and IP bans that need rotating residential proxies and browser fingerprinting to clear. ReefAPI handles all of that for you — no proxies, no captchas, no maintenance — and returns live JSON. Blocked or failed calls are free.