Change Trace MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CHANGE_TRACE_EXTERNAL_ADAPTERS_FILE | No | File path for registering external adapters |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_server_info | Return diagnostic metadata for this Change Trace MCP process. Use this to verify host startup and runtime compatibility. |
| get_compatibility_fixture | Return a fixed, versioned JSON fixture. The same package version must return byte-identical text in every MCP Host. |
| get_change_scope | Resolve two Git refs and return a deterministic, bounded summary of commits, changed files, diff excerpts, detected languages, truncation, and read errors. The repository path must be an explicit Git root. |
| collect_local_evidence | Collect bounded, provenance-rich excerpts from regular files beneath configured document roots in the exact Git repository named by a ChangeScope. Symbolic links are not followed and common credential patterns are redacted. |
| get_review_bundle | Combine a ChangeScope, local document evidence, and optional normalized evidence into a bounded ReviewBundle with a stable evidence index, deterministic Git facts, and explicit missing-evidence records. |
| validate_findings | Validate Agent-produced findings against the shared schema and a ReviewBundle. Known enum formatting aliases are normalized; unknown evidence IDs, unsupported sources, duplicate IDs, and unsupported substantive findings are rejected without inventing content. |
| write_reportA | Render validated Agent findings as a deterministic Markdown and JSON report pair inside a repository-relative output directory. The report preserves confirmed, suspected, and inconclusive findings, evidence coverage, bundle limits/truncation, and validation warnings. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion between tools.
With a single tool, naming is trivially consistent; the name 'write_report' is clear and follows a verb_noun pattern.
A single tool is borderline appropriate for a server focused solely on report generation, but the narrow scope suggests the server may be too minimal for broader use cases.
The tool only writes reports but does not include tools for managing findings or inputs, leaving gaps that would require external systems to function.