did-it
Audits claimed actions (edits, creates, deletes) against the actual Git working tree, verifying which claimed changes are truly present and rejecting those with no evidence.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@did-it verify the changes I claim to have made"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
did-it
Stop letting coding agents congratulate themselves.
When a coding agent finishes a task, you review a summary the agent wrote about itself. Research on 5,851 real developer sessions found that those self-reports referred to about one action in eleven — and a reader working from the report alone recovered roughly a fifth of the action log (arXiv:2609.12205).
did-it is the missing gate: an autonomous self-auditing MCP server. The agent must call verify_claimed_actions against your Git working tree before it is allowed to say "Done." Ghost claims are a hard rejection. The user never sees a victory lap that Git cannot back.
Agent finishes coding
↓
.cursorrules mandates verify_claimed_actions
↓
MCP tool checks git status / diff
↓
Ghost claims → 🛑 hard rejection (fix or admit failure)
Verified → ✅ completion allowed30-second verification
git clone https://github.com/preprint-labs/did-it.git
cd did-it
npm install
npm test
npm run build
node dist/index.js --cli --text "I created src/index.ts"You should see a receipts table, an honesty score, and can_report_completion: true|false. Exit code 1 means a ghost claim.
Related MCP server: execution-proofs
Install in Cursor (mcp.json)
Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (user):
{
"mcpServers": {
"did-it": {
"command": "node",
"args": ["<FULL_PATH_TO_DID_IT>/dist/index.js"]
}
}
}Point args at your built dist/index.js. Windows example: "C:\\path\\to\\did-it\\dist\\index.js". In this repo, .cursor/mcp.json uses a relative dist/index.js so no machine-specific absolute path is committed.
The server audits process.cwd() of the host workspace (the project the agent is editing), not the did-it repo itself. Override with DID_IT_WORKSPACE if needed.
2-line rule (paste into .cursorrules)
Before declaring a task complete or outputting your final summary, you MUST call `verify_claimed_actions` with a list of all changes you claim to have made. If any ghost claims are flagged, you must execute the missing changes before responding to the user.Claude Code
claude mcp add did-it -- node "<FULL_PATH_TO_DID_IT>/dist/index.js"Or in ~/.claude.json / project MCP config:
{
"mcpServers": {
"did-it": {
"command": "node",
"args": ["<FULL_PATH_TO_DID_IT>/dist/index.js"]
}
}
}Windows example: "C:\\path\\to\\did-it\\dist\\index.js".
Add the same 2-line rule to CLAUDE.md.
GitHub Copilot (VS Code)
mcp.json in .vscode/mcp.json or your Copilot MCP settings:
{
"servers": {
"did-it": {
"command": "node",
"args": ["<FULL_PATH_TO_DID_IT>/dist/index.js"]
}
}
}MCP tools
Tool | What it does |
| Audit claimed edits/creates/deletes/installs against |
| Raw list of files that actually changed. Use this instead of guessing. |
Hard rejection text:
🛑 [did-it Verification Failed]: You claimed to have completed tasks that have zero evidence in Git: ${ghost_claims}. You are PROHIBITED from reporting completion to the user until these actions are physically executed or explicitly admitted as failed.
honesty_score is verified / (verified + ghost) in [0.0, 1.0]. UNVERIFIABLE rows (e.g. "ran tests" with no artifact) are shown but excluded. can_report_completion is true iff there are zero ghost claims.
CLI fallback
MCP is primary. For a one-off local audit:
node dist/index.js --cli
node dist/index.js --cli --text "I updated src/index.ts and created src/ghost.ts"
echo "created README.md" | node dist/index.js --cli--cli with no claims prints the real uncommitted file list. --root <path> sets the workspace.
Cite
@article{kraishan2026plans,
title = {Plans They Abandon, Reports They Author: The Narrative Layer of Autonomous Agents},
author = {Kraishan, Obada and Jitkajornwanich, Kulsawasd},
journal = {arXiv preprint arXiv:2609.12205},
year = {2026}
}License
MIT
Available Tools
2 toolsinspect_actual_changesA
Return the raw list of files that are actually modified, created, deleted, or untracked in Git. Use this instead of guessing what changed.
Inputs: no named parameters.
verify_claimed_actionsA
Verify a list of claimed coding actions against the local Git working tree before reporting completion. Call this with every file you claim to have created, edited, deleted, or every package you claim to have installed. Ghost claims are a hard rejection: you must execute the missing work or admit failure before the user sees a completion summary.
Inputs: claims (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one inspects raw Git changes, the other verifies claimed actions against the working tree. No overlap or ambiguity; an agent can easily select the right tool.
Both tool names follow a consistent verb_noun pattern: 'inspect_actual_changes' and 'verify_claimed_actions'. The verbs are descriptive and the structure is uniform.
With only 2 tools, the server feels minimal, but its purpose is narrowly scoped to Git verification. The two tools cover the core inspection and verification workflows, so the count is appropriate for the domain, though it edges toward thinness.
The tool surface fully covers the server's stated purpose of checking actual Git state and verifying claims against it. There are no obvious dead ends or missing operations for this verification-focused domain; it provides the essential inspect and verify capabilities.
Related MCP Connectors
Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.
Git-native policy layer for AI agents: check_action verdicts against rules approved via PR.
Lets coding agents check their own code for leaked secrets, risky dependencies and AI-code mistakes
Verify what your AI coding agent built: test coverage, recorded browser tests, a done verdict.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables verification of AI coding agent self-reports against git diff truth and a deterministic gate, producing pass/regenerate/reject directives to ensure claimed work matches actual changes.6144 PyPIAGPL 3.0
- AlicenseBqualityCmaintenanceVerifies AI agent completion claims by checking that claimed output files exist and are fresh, acting as a lightweight physical telemetry gate.19 npm6MIT
- AlicenseNot gradedqualityDmaintenanceDetects and reports when AI coding agents modify files outside their declared task scope, comparing declared globs and categories with actual changes.50 PyPIMIT
- FlicenseAqualityBmaintenanceEnables coding agents to perform workspace-confined file operations, read-only Git inspection, and structured shell commands, while requiring out-of-band human approval for mutations and external executions and maintaining an audit trail.143-