Skip to main content
Glama
Sign In
murphy-mcp

murphy-mcp

by lucianomanetta
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Record the workspace as it is now

checkpoint

Records an independent workspace snapshot before an agent starts work, capturing file paths, sizes, modification times, SHA-256 hashes, and git state, then returns an ID for later comparison.

Instructions

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.

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": {
      "root": "<root>"
    },
    "name": "checkpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
rootYesAbsolute path to the workspace to observe. Use the project root the agent is working in.
labelNoA short name for this checkpoint, such as the task it precedes.
ignoreNoExtra directory names to skip, matched on a single path segment.
maxFilesNoStop the walk after this many files. Default 50000.
maxFileBytesNoDo not hash files larger than this. Default 8388608.
noDefaultIgnoresNoAlso scan .git, node_modules and .murphy. Off by default.

Output Schema

NameRequiredDescriptionDefault
gitYes
rootYes
ignoredYes
takenAtYes
fileCountYes
truncatedYes
checkpointIdYes
truncatedReasonNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, and the description adds real context beyond them: the provenance guarantee ('Nothing here comes from the agent') and the full inventory of what is observed. It does not explain that repeated calls create distinct checkpoints or what happens on huge trees, leaving the non-idempotent hint partly unaddressed.

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

Conciseness5/5

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

Three short sentences: what is captured, what is returned, and the ordering instruction. Front-loaded, no filler, and the unusual provenance claim is placed where it matters.

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?

An output schema exists, so return shape need not be explained, and the description still states it returns a checkpoint id. The remaining gap is lifecycle context — that the record persists server-side and how the id is consumed by evidence_since or check_claims — which would help an agent chain calls.

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%, and each parameter (root, label, ignore, maxFiles, maxFileBytes, noDefaultIgnores) already carries its own documentation and defaults. The description adds no parameter-level meaning beyond the schema, so the baseline applies.

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 names a concrete operation and enumerates exactly what gets captured (file paths, sizes, mtimes, SHA-256s, plus git HEAD, branch and working-tree status), so an agent knows precisely what this tool produces rather than guessing from the name 'checkpoint'.

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

Usage Guidelines4/5

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

'Call this first' gives explicit ordering guidance relative to the agent's workflow, which is the key usage rule here. It stops short of naming the siblings (check_claims, evidence_since, list_checkpoints) or stating when a second checkpoint is warranted, so it is clear context without explicit alternatives.

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