Meridian

List Repository Branches and Commits

github_refs_list

Read-only

Lists the branches and recent commits of the GitHub repository connected to an app, as Meridian sees them. Use this to get a real git_sha for deployment_create instead of guessing one: a sha that has not been pushed to the connected repository will fail during the build rather than at the tool call.

Returns repository (owner/name plus connected), branches (each with name, commit_sha, protected) and commits (each with sha, message, author, date).

Pass branch to list commits from a specific branch; the repository's default branch is used otherwise. An app with no connected repository reports connected: false with empty lists rather than an error, as do an empty repository and an unknown branch.

Takes the app_id from apps_list. Requires the hosting.view permission on the app, like environments_list.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "app_id": "<app_id>"
    },
    "name": "github_refs_list"
  }
}

Input Schema

Name	Required	Description
`app_id`	Yes	The app uuid returned by `apps_list`.
`branch`	No	List commits from this branch. Defaults to the repository default branch.
`organization_id`	No	An organisation uuid or slug. When supplied, `app_id` is resolved within that organisation and may be a slug instead of a uuid, mirroring the Meridian web app.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the readOnly/openWorld annotations, it discloses the failure model (unpushed sha fails at build, not at call), the non-error degradation for unconnected apps, empty repos and unknown branches, and the required permission. These are exactly the behaviors an agent cannot infer from annotations or schema.

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?

The core purpose and the deployment_create motivation are front-loaded, and each paragraph covers a distinct concern (purpose, return shape, parameters, edge cases, permissions). It is slightly verbose, with the edge-case sentence carrying some repetition, but no sentence is wasted.

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?

With no output schema, the description compensates by enumerating the returned fields (repository, branches, commits) with their sub-fields. Combined with permission and edge-case disclosure, an agent has everything needed to call it correctly and interpret results.

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 app_id, branch and organization_id are already documented. The description restates the branch default behavior and the app_id source but says nothing about organization_id's slug/uuid resolution, so it adds little beyond the schema baseline.

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 opens with a specific verb and resource ('Lists the branches and recent commits of the GitHub repository connected to an app') and scopes it to how Meridian sees the repo. It is clearly distinct from siblings like apps_list and environments_list, which supply inputs rather than repo data.

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?

It gives an explicit use case and the alternative it replaces: get a real git_sha here rather than guessing one for deployment_create, with the consequence of guessing stated. It also names prerequisites (app_id from apps_list, hosting.view permission) and the fallback behavior for unknown branches.

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

All Meridian tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?