GitFlic MCP Server

gitflic_mr_merge

Destructive

Merges a merge request in GitFlic, optionally setting merge or squash commit messages. Fails with MergeCheckException when branch protection requires more approvals.

Instructions

Merge a merge request. May fail with MergeCheckException if branch protection requires more approvals.

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": {
      "project": "<project>",
      "id": "<id>"
    },
    "name": "gitflic_mr_merge"
  }
}

Input Schema

Name	Required	Description
`id`	Yes
`raw`	No	Return the full, un-slimmed GitFlic response for THIS call (no token compression). Use when the default slim view dropped a field you need.
`message`	No	Merge commit message
`project`	Yes
`squashMessage`	No	Squash commit message (if squash enabled)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.5.1Nov 13, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, so the safety profile is covered structurally. The description contributes a genuinely useful non-obvious behavioral fact — the MergeCheckException failure mode tied to branch protection — but says nothing about irreversibility, what happens to the source branch, or what a successful merge returns.

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?

Two short sentences with zero padding, and the core action is front-loaded ahead of the failure caveat. It is efficiently sized, though the failure clause could have been attached without losing anything.

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

Completeness3/5

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

With no output schema and 40% of parameters undocumented, the description should carry more weight than it does for a destructive, non-idempotent operation. The failure mode is a good addition, but the meaning of the required identifiers and the post-merge state remain unexplained.

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

Parameters2/5

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

Schema coverage is 60%, leaving the two required parameters (project and id) with no descriptions in either the schema or the description. For a destructive mutation this is the key ambiguity: it is never stated whether 'id' is a merge request ID or number, or whether 'project' expects a key, path, or numeric ID.

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?

The description gives a specific verb+resource ("Merge a merge request"), which cleanly separates it from siblings such as gitflic_mr_approve, gitflic_mr_close and gitflic_mr_edit. It does not explicitly name a sibling or contrast with one, so it stops short of a 5.

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

Usage Guidelines3/5

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

Usage is only implied: the note about branch protection hints that merging should follow sufficient approvals, but there is no explicit when-to-use / when-not-to-use guidance and no pointer to gitflic_mr_approve as the remediation path. The reader must infer the workflow.

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

Deploy Server