Skip to main content
Glama
Sign In
phabricator-mcp

phabricator-mcp

by freelancer
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

phabricator_feed_query

Read-only

Query the Phabricator activity feed to retrieve recent task updates, revision changes, and commits, returned as an object keyed by story PHID.

Instructions

Query the Phabricator activity feed. Returns recent activity (task updates, revision changes, commits, etc.) as an object keyed by story PHID. Uses feed.query (the only Conduit method for feed data).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "phabricator_feed_query"
  }
}

Input Schema

NameRequiredDescriptionDefault
viewNoOutput format: "data" (structured, default), "text" (human-readable), "html" (rendered HTML), "html-summary" (title only)
afterNochronologicalKey (string): return older stories
limitNoMaximum results (max 100)
beforeNochronologicalKey (string): return newer stories
filterPHIDsNoOnly show activity involving these PHIDs (user, project, task, etc.)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv2.1.0
    • changedInput schema / properties / after / description
      Previous value: -"Cursor for pagination (chronological key from previous results)"New value: +"chronologicalKey (string): return older stories"
    • changedInput schema / properties / after / type
      Previous value: -"number"New value: +"string"
    • changedInput schema / properties / before / description
      Previous value: -"Cursor for reverse pagination"New value: +"chronologicalKey (string): return newer stories"
    • changedInput schema / properties / before / type
      Previous value: -"number"New value: +"string"
  2. First observedv2.0.19

TDQS

B3.2/5.0
Behavior3/5

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

readOnlyHint=true already establishes this is a safe read, so the bar is lower. The description adds useful context by naming the return format and the underlying Conduit method, but says nothing about ordering, pagination behavior via after/before, or what happens when filterPHIDs matches nothing.

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

Conciseness4/5

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

Three short sentences that are front-loaded with the core action and return shape; nothing is padded. The final sentence about feed.query is marginal but does help an agent understand there is no alternative endpoint.

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?

There is no output schema, so the description correctly spends a sentence on the return shape. With 100% schema coverage on all optional params, the only real gap is selection guidance versus sibling search tools.

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 description coverage is 100%, so all five parameters (view, after, before, limit, filterPHIDs) are already documented in the schema, including the enum values. The description adds no parameter-level meaning beyond that baseline.

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

Purpose4/5

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

States a specific verb and resource ("Query the Phabricator activity feed") and scopes the content with examples (task updates, revision changes, commits). The return shape (object keyed by story PHID) is also named. It does not explicitly distinguish itself from the closest sibling, phabricator_transaction_search, which also surfaces object activity.

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?

The description says what the tool returns but never says when to choose it over transaction_search, task_search, or the per-object search siblings. The parenthetical "the only Conduit method for feed data" justifies the implementation rather than guiding tool selection.

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