ActivityPub MCP Server

Search Fediverse

search

Read-only

Find accounts, posts, or hashtags from any fediverse instance. Enter a query to search across the decentralized network.

Instructions

Unified search across the fediverse - find accounts, posts, or hashtags on any instance

Input Schema

TableJSON Schema

Name	Required	Description
`query`	Yes	Search query
`domain`	No	Instance domain to search on (default: mastodon.social)
`type`	No	Type of content to search for (default: all)
`limit`	No	Number of results per type (default: 10)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`accounts`	No
`statuses`	No
`hashtags`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv3.1.4Jun 17, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "accounts": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "followers": {
+            "type": "string"
+          },
+          "following": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "inbox": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          },
+          "outbox": {
+            "type": "string"
+          },
+          "preferredUsername": {
+            "type": "string"
+          },
+          "summary": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "id"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "hashtags": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "name": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "name"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "statuses": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "author": {
+            "description": "Author handle or display name",
+            "type": "string"
+          },
+          "content": {
+            "description": "Plain-text/summarized post body",
+            "type": "string"
+          },
+          "contentWarning": {
+            "description": "Content warning / summary, if any",
+            "type": "string"
+          },
+          "createdAt": {
+            "description": "ISO timestamp",
+            "type": "string"
+          },
+          "favourites": {
+            "type": "number"
+          },
+          "id": {
+            "description": "Post/status ID",
+            "type": "string"
+          },
+          "reblogs": {
+            "type": "number"
+          },
+          "replies": {
+            "type": "number"
+          },
+          "type": {
+            "description": "ActivityPub object type (Note, Announce, …)",
+            "type": "string"
+          },
+          "url": {
+            "description": "Canonical URL of the post",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "content"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

First observedv0.1.0Jun 4, 2026

TDQS

A3.6/5.0

Behavior3/5

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

The readOnlyHint annotation already communicates that this is a safe read operation. The description adds that it searches across instances, but doesn't disclose additional behavioral traits like pagination, result ordering, or whether it only searches public content. With annotations covering safety, a 3 is appropriate – the description adds some context but is not rich.

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?

The description is a single sentence that is front-loaded with the core action ('Unified search') and then specifies the searchable content types. It is concise with no wasted words.

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

Completeness4/5

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

Given that the tool has 4 parameters, an output schema, and a readOnly annotation, the description is mostly complete. It covers the scope (any instance) and types of content. Minor gaps: it doesn't explicitly state that results come from the specified domain or default instance, and doesn't mention public-only searches. But the output schema likely clarifies return structure.

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

Parameters3/5

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

Schema coverage is 100%, so the baseline is 3. The description mentions 'accounts, posts, or hashtags', which corresponds to the 'type' parameter, but adds no additional detail beyond the schema for any parameter. It does not explain the 'domain' or 'limit' parameters further.

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?

The description clearly states the tool's purpose: 'Unified search across the fediverse - find accounts, posts, or hashtags on any instance'. It uses a specific verb ('search') and identifies the resource (fediverse content) and scope (any instance). This distinguishes it from siblings like get-trending-posts or discover-actor.

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

Usage Guidelines2/5

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

No explicit guidance is provided on when to use this tool versus alternatives. The description does not mention when not to use it, nor does it reference sibling tools that might be more appropriate for specific tasks (e.g., get-trending-posts for trends). The implied usage is 'for any federated search', but without exclusions or context.

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

Deploy Server