MCP Registry API — Server Metadata Export

MCP Registry API for server metadata. Search the official Model Context Protocol Registry and export normalized records through the Apify API, schedules, webhooks, or dataset downloads. This Actor reads one official MCP server registry and never scrapes third-party directories or mirrors package binaries.

Actor ID multi-registry-mcp-intelligence is a stable legacy identifier. The product scope is search and export from one official Registry only, not multi-registry aggregation.

Why use this Actor

• MCP server name, namespace, description, and lifecycle status
• Published version and update date when provided
• Repository metadata when the Registry record includes it
• Source-backed URLs and retrieval timestamps
• JSON, CSV, Excel, XML, RSS, and API access through Apify datasets

Use it for MCP server discovery, internal catalog building, registry snapshots, and agent-tool research. It is a search-and-export API for one official registry, not a security scanner or a multi-registry aggregator.

Quick start

1. Add one or more server names, namespaces, or search terms.
2. Choose a per-query match limit from 1 to 100.
3. Run the Actor and download the dataset or read it through the Apify API.

{
  "queries": ["mcp"],
  "maxItems": 10
}

The Actor loads official Registry records and matches each query against their published metadata. Add up to 20 queries and request 1–100 matches per query.

Example output

{
  "recordType": "result",
  "query": "mcp",
  "sourceId": "ac.inference.sh/mcp",
  "title": "ac.inference.sh/mcp",
  "description": "Run AI applications through an MCP server.",
  "status": "active",
  "updatedAt": "2026-04-13T00:00:00.000Z",
  "metadata": {
    "version": "1.0.0",
    "repository": {}
  },
  "sourceName": "Official MCP Registry"
}

The Registry may omit repository or date fields. Missing source data remains missing instead of being inferred.

Input

Field	Type	Required	Description
queries	string[]	Yes	Server names, namespaces, or terms to match against official Registry records. Up to 20.
maxItems	integer	No	Matching records stored per query, from 1 to 100. Default: 25.
canaryMode	boolean	No	Returns one no-network release-status row for deterministic platform QA.

Output data contract

Each row uses the stable fields recordType, query, sourceId, title, description, status, url, publishedAt, updatedAt, metrics, metadata, sourceName, sourceUrl, retrievedAt, and releaseState.

The OUTPUT record in the default key-value store reports the item count, empty-query count, network use, release state, and any mandatory notice.

Automate it

• Run recurring Registry snapshots with Apify Schedules
• Trigger downstream catalog updates with webhooks
• Read the dataset from the Apify API
• Export to JSON, CSV, Excel, or another supported dataset format

For a buyer-focused guide and integration examples, see the Official MCP Registry API page.

Limitations and responsible use

• Source: Official MCP Registry API
• Registry overview: Official MCP Registry
• Aggregator guidance: Registry aggregators
• Terms: MCP Registry Terms of Service
• Independent product; not affiliated with, endorsed by, or sponsored by the Model Context Protocol project
• Official Registry metadata only
• No Glama, Smithery, MCP.so, or other third-party registry data
• No package binary mirroring or security scoring
• Registry metadata is published under the Registry's documented CC0 terms
• HTTPS source hosts are allowlisted; responses, retries, and timeouts are bounded
• Empty searches produce an explicit emptyResult row and are not charged

API comparison

Option	Best for	Important boundary
Official Registry API	Direct ingestion with custom cursor handling	You own matching, normalization, storage, and exports
This Actor	Searchable Registry snapshots in normalized Apify datasets	One official source only; no multi-registry deduplication or stored history

Validation evidence

On 2026-07-23, the bounded source canary returned 100 complete official Registry records and an opaque next cursor. On 2026-07-24, actor-specific live QA returned five non-empty records from the deployed build.

Pricing

The primary pay-per-event charge is result-item.

• List price: $0.002 per successfully stored source record
• Apify plan tiers: $0.0018, $0.0016, or $0.0014 per record
• Canary, empty-result, and failed rows are not charged
• Maximum valid input: 20 queries × 100 records = 2,000 source records, or $4.00 maximum list-price PPE charge per run
• Duplicate query strings are removed before requests; if the same source record matches two different queries, each stored row is charged

Apify platform compute charges and plan credits are shown separately by Apify.

Support

For a reproducible issue, include the public query, expected behavior, run ID, and the Registry record or namespace involved. Never send package credentials or private server configuration.

FAQ

Is this a multi-registry scraper?

No. Despite the legacy Actor slug, the runtime reads only the official Model Context Protocol Registry.

Does it test MCP servers?

No. It exports published Registry metadata and does not execute or security-scan listed servers.

Can it monitor changes?

You can schedule repeated snapshots and compare datasets downstream. The Actor itself does not maintain a historical diff database.