Skip to main content
Glama
Sign In
apify

actors-mcp-server

Official
by apify
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Fetch Actor details

fetch-actor-details
Read-onlyIdempotent

Retrieve detailed Actor information by ID or full name—including documentation, input schema, pricing, stats, and HTTP operations—and select only needed fields to reduce token usage.

Instructions

Get detailed information about an Actor by its ID or full name (format: "username/name", e.g., "apify/rag-web-browser").

Requires the exact ID or full name — do not construct a plausible-looking name and call this tool with it. If you only have a description, a partial name, or a name you have not seen in this conversation, find it with search-actors first.

Use 'output' to control returned information:

  • Default: all fields except outputSchema and serverInterface.

  • Selective: set only the fields you need to true, e.g. output: { inputSchema: true }

  • Common patterns: inputSchema only, description + readme, serverInterface: true (every operation in full when they fit, one line per operation otherwise) or "GET /search" (one operation in full) for Server Actors

The 'readme' field returns the summary when available, full README otherwise. Use when querying Actor details, documentation, or input requirements. It does not connect to an MCP server Actor; fetch-actor-mcp-tool-list lists its MCP tools.

EXAMPLES:

  • What does apify/web-fetch do?

  • What is the input schema for apify/web-scraper?

  • What HTTP operations does this Server Actor expose?

Input Schema

NameRequiredDescriptionDefault
actorYesActor ID or full name in the format "username/name", e.g., "apify/rag-web-browser".
outputNoSpecify which information to include in the response to save tokens.

Output Schema

NameRequiredDescriptionDefault
readmeNoActor README summary when available, otherwise the full README documentation.
actorInfoNo
inputSchemaNoActor input schema.
outputSchemaNoOutput schema inferred from successful runs.
serverInterfaceNoThe Actor's server interface. `output.serverInterface: true` returns every operation with its parameters and request body schema when they fit, or one line per operation otherwise. A "METHOD /path" string returns that one operation in full.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.20.0
    • changedInput schema / properties / output / properties / serverInterface / description
      Previous value: -"Server Actor HTTP API. true: full schema with guidance when it fits; otherwise operation navigation.\n\"METHOD /path\" (e.g. \"GET /search\"): operation excerpt. \"#/...\": raw node at a local JSON pointer.\nEach section is limited to 262144 UTF-8 bytes including guidance. References are not expanded or fetched."New value: +"Server Actor HTTP API. true: every operation with its parameters and request body schema when they fit; otherwise one line per operation.\n\"METHOD /path\" (e.g. \"GET /search\"): that one operation in full.\nEach is limited to 262144 UTF-8 bytes."
    • changedOutput schema / properties / serverInterface / description
      Previous value: -"The Actor's server interface. `output.serverInterface: true` returns the full API schema with guidance when it fits, or operation navigation otherwise. A \"METHOD /path\" string returns an operation excerpt; \"#/...\" returns a raw local schema node."New value: +"The Actor's server interface. `output.serverInterface: true` returns every operation with its parameters and request body schema when they fit, or one line per operation otherwise. A \"METHOD /path\" string returns that one operation in full."
  2. Changed5 schema fields changedv0.19.5
    • removedInput schema / properties / output / properties / mcpTools
      Removed value: -{
-  "description": "List available tools (only for MCP server Actors).",
-  "type": "boolean"
-}
    • addedInput schema / properties / output / properties / serverInterface
      Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "type": "string"
+    }
+  ],
+  "description": "Server Actor HTTP API. true: full schema with guidance when it fits; otherwise operation navigation.\n\"METHOD /path\" (e.g. \"GET /search\"): operation excerpt. \"#/...\": raw node at a local JSON pointer.\nEach section is limited to 262144 UTF-8 bytes including guidance. References are not expanded or fetched."
+}
    • removedOutput schema / properties / actorInfo / properties / stats / properties / bookmarks
      Removed value: -{
-  "description": "Number of bookmarks",
-  "type": "number"
-}
    • removedOutput schema / properties / mcpTools
      Removed value: -{
-  "description": "Markdown listing of MCP tools exposed by the Actor (only present when `output.mcpTools` is requested).",
-  "type": "string"
-}
    • addedOutput schema / properties / serverInterface
      Added value: +{
+  "description": "The Actor's server interface. `output.serverInterface: true` returns the full API schema with guidance when it fits, or operation navigation otherwise. A \"METHOD /path\" string returns an operation excerpt; \"#/...\" returns a raw local schema node.",
+  "type": "string"
+}
  3. Changed1 schema field changedv0.18.3
    • addedOutput schema / properties / actorInfo / properties / inputFields / properties / properties / additionalProperties / properties / type / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  }
+]
  4. Changed1 schema field changedv0.14.2
    • removedOutput schema / properties / actorInfo / properties / stats / properties / successRate
      Removed value: -{
-  "description": "Success rate percentage",
-  "type": "number"
-}
  5. Changed2 schema fields changedv0.11.5
    • addedOutput schema / properties / actorInfo / properties / pictureUrl
      Added value: +{
+  "description": "Actor picture URL",
+  "type": "string"
+}
    • changedOutput schema / properties / actorInfo / properties / pricing / required
      Previous value: -[
-  "model",
-  "userTier"
-]New value: +[
+  "model"
+]
  6. First observedv0.10.13

TDQS

A4.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only/idempotent/non-destructive, so the description correctly spends its budget elsewhere: it discloses the default field set ("all fields except outputSchema and serverInterface"), the summary-vs-full README behavior, and that it does not connect to an MCP Server Actor. It does not mention auth requirements or any size/rate caveats beyond the per-field byte limit already in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the identifier requirement and the anti-hallucination warning before the optional output tuning. Bulleted output modes and example questions are scannable, and no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter read tool with full schema coverage, annotations, and an output schema, the description covers everything an agent needs: identifier format, the failure mode to avoid, fallback sibling, and how to control response size.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline would be 3; the description earns above that by documenting the default output composition and giving concrete selective patterns (inputSchema only, description + readme, serverInterface true vs. "GET /search"). The readme summary/full nuance is restated from the schema but the default and usage patterns are genuinely new information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb + resource ("Get detailed information about an Actor by its ID or full name") with the accepted identifier format spelled out. It also differentiates itself from siblings by noting it does not connect to an MCP Server Actor and that fetch-actor-mcp-tool-list handles MCP tool listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states the precondition ("Requires the exact ID or full name — do not construct a plausible-looking name") and routes the agent to search-actors when it has only a description or partial name. Example queries at the end map user intents to this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools