AT Protocol MCP Server

get_custom_feed

Read-only

Retrieve posts from any custom algorithm feed using its AT-URI. Returns feed metadata and paginated posts; use the cursor to get more pages.

Instructions

Get posts from a custom algorithm feed. Works without authentication; richer with auth. Returns feed generator metadata and a paginated list of posts; use the returned cursor to fetch subsequent pages. Use get_timeline for the authenticated user's home feed instead. Subject to per-tool rate limiting.

Input Schema

TableJSON Schema

Name	Required	Description
`feedUri`	Yes	AT-URI of the custom algorithm feed generator (at://did/app.bsky.feed.generator/rkey).
`limit`	No	Max posts to return per page (1–100, default 50).
`cursor`	No	Opaque pagination cursor from the previous response cursor field; omit for the first page.

Output Schema

TableJSON Schema

Name	Required	Description
`success`	Yes	Whether the feed was retrieved successfully.
`feed`	Yes	Metadata about the feed generator.
`posts`	Yes	Paginated posts from the feed.
`cursor`	No	Pagination cursor for the next page; absent when no more pages.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.6.2Jun 23, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```

Changed4 schema fields changedv0.6.0Jun 11, 2026

addedInput schema / properties / cursor / description

Added value: +"Opaque pagination cursor from the previous response cursor field; omit for the first page."

addedInput schema / properties / feedUri / description

Added value: +"AT-URI of the custom algorithm feed generator (at://did/app.bsky.feed.generator/rkey)."

addedInput schema / properties / limit / description

Added value: +"Max posts to return per page (1–100, default 50)."

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "cursor": {
+      "description": "Pagination cursor for the next page; absent when no more pages.",
+      "type": "string"
+    },
+    "feed": {
+      "description": "Metadata about the feed generator.",
+      "properties": {
+        "creator": {
+          "description": "Optional profile of the feed creator (present when generator metadata is available).",
+          "properties": {
+            "did": {
+              "description": "DID of the creator.",
+              "type": "string"
+            },
+            "displayName": {
+              "description": "Optional display name of the creator.",
+              "type": "string"
+            },
+            "handle": {
+              "description": "Handle of the creator.",
+              "type": "string"
+            }
+          },
+          "required": [
+            "did",
+            "handle"
+          ],
+          "type": "object"
+        },
+        "description": {
+          "description": "Optional description of the feed.",
+          "type": "string"
+        },
+        "displayName": {
+          "description": "Optional display name of the feed.",
+          "type": "string"
+        },
+        "uri": {
+          "description": "AT-URI of the feed generator.",
+          "type": "string"
+        }
+      },
+      "required": [
+        "uri"
+      ],
+      "type": "object"
+    },
+    "posts": {
+      "description": "Paginated posts from the feed.",
+      "items": {
+        "properties": {
+          "author": {
+            "description": "Author of the post.",
+            "properties": {
+              "avatar": {
+                "description": "Optional avatar image URL.",
+                "type": "string"
+              },
+              "did": {
+                "description": "DID of the author.",
+                "type": "string"
+              },
+              "displayName": {
+                "description": "Optional display name.",
+                "type": "string"
+              },
+              "handle": {
+                "description": "Handle of the author.",
+                "type": "string"
+              }
+            },
+            "required": [
+              "did",
+              "handle"
+            ],
+            "type": "object"
+          },
+          "cid": {
+            "description": "CID of the post.",
+            "type": "string"
+          },
+          "createdAt": {
+            "description": "ISO 8601 timestamp when the post was created.",
+            "type": "string"
+          },
+          "isLiked": {
+            "description": "Whether the authenticated user has liked this post.",
+            "type": "boolean"
+          },
+          "isReposted": {
+            "description": "Whether the authenticated user has reposted this post.",
+            "type": "boolean"
+          },
+          "likeCount": {
+            "description": "Number of likes.",
+            "type": "number"
+          },
+          "replyCount": {
+            "description": "Number of replies.",
+            "type": "number"
+          },
+          "repostCount": {
+            "description": "Number of reposts.",
+            "type": "number"
+          },
+          "text": {
+            "description": "Plain text content of the post.",
+            "type": "string"
+          },
+          "uri": {
+            "description": "AT-URI of the post.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "uri",
+          "cid",
+          "author",
+          "text",
+          "createdAt",
+          "replyCount",
+          "repostCount",
+          "likeCount",
+          "isLiked",
+          "isReposted"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "success": {
+      "description": "Whether the feed was retrieved successfully.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "success",
+    "feed",
+    "posts"
+  ],
+  "type": "object"
+}

Changed1 schema field changedv0.3.0Jun 9, 2026
- removedInput schema / $schema
```
Removed value: -"http://json-schema.org/draft-07/schema#"
```
First observedv0.2.1Jun 2, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond annotations (readOnlyHint=true, openWorldHint=true), the description adds meaningful behavioral traits: authentication variability, pagination cursor mechanism, return structure (feed generator metadata + posts), and rate limits. No contradictions with annotations.

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?

Four concise sentences, front-loaded with the core purpose, no redundant or irrelevant information. Every sentence contributes distinct value (purpose, auth, pagination, sibling distinction, rate limit).

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?

Covers all essential aspects for selecting and invoking this tool: purpose, authentication, pagination, sibling differentiation, and rate limiting. With an output schema present, the description does not need to detail return values further.

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 schema already documents 'feedUri', 'limit', and 'cursor' thoroughly. The description adds the cursor pagination hint but otherwise doesn't exceed the schema's parameter descriptions, justifying the baseline score of 3.

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 retrieves posts from a custom algorithm feed, specifying the resource ('custom algorithm feed') and action ('get posts'). It explicitly distinguishes from the sibling 'get_timeline' by naming the alternative use case.

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?

Provides explicit guidance on when to use this tool ('use get_timeline for the authenticated user's home feed instead') and notes authentication levels ('works without authentication; richer with auth'). Also mentions rate limiting, helping the agent decide contextually.

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