murphy-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 |
|---|---|
| checkpointA | Takes an independent record of the workspace before an agent starts work: every file path, size, modification time and SHA-256, plus the git HEAD, branch and working-tree status read from the repository. Returns a checkpoint id. Call this first. Nothing here comes from the agent. |
| evidence_sinceA | Rescans the workspace and reports every file added, modified or deleted since the checkpoint, together with what moved in git. This is the observed record. It does not know and does not ask what any agent intended or reported. |
| check_claimsA | Takes what the agent said it did and compares it with what the machine shows. Returns four separate buckets: confirmed (claimed and observed), contradicted (claimed but nothing changed), unreported (changed and never mentioned), and unverifiable (claims a filesystem and git record cannot settle, such as 'the tests pass' or 'the bug is fixed'). The buckets are never merged, because a claim is not evidence. |
| list_checkpointsA | Lists the checkpoints stored under the workspace, most recent first. |
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 4 tools
Each tool has a clearly distinct role in the verification lifecycle: creating a checkpoint, listing checkpoints, reporting observed changes since a checkpoint, and comparing agent claims against observations. The descriptions sharply separate observed evidence from claimed work, making misselection unlikely.
The set mixes naming conventions: check_claims and list_checkpoints follow a verb_noun pattern, while checkpoint is a bare noun/verb and evidence_since is a noun_preposition phrase. The names are still readable and descriptive, but the pattern is not uniform.
Four tools are well-scoped for a focused evidence-and-verification server. Each tool supports a distinct, necessary part of the workflow without redundancy.
The surface covers checkpoint creation, enumeration, observed diffs, and claim verification, which are the core operations. Minor gaps exist, such as retrieving details for a single checkpoint by id or cleaning up/deleting old checkpoints, but agents can work around these limitations.