io.github.datumline/agent-guard
OfficialServer 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.
Call verify_completion_claim before accepting any agent's 'done'.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| verify_completion_claimA | Check an AI agent's claim that a job is done against the artifacts it says it produced. Returns a JSON receipt whose 'verdict' is VERIFIED (every artifact present and passing), FAILED (an artifact fails a check), FALSE_DONE (the job is claimed COMPLETED/DONE but an artifact is missing) or UNVERIFIABLE (the manifest names no artifacts). Treat anything other than VERIFIED as not done. Artifact types: file (path, min_bytes, min_lines, must_contain, sha256), json (path, required_keys), url (url, status, must_contain). Relative paths resolve against the server's working directory. |
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
There is only one tool, so there is no possibility of selecting the wrong tool or confusing it with another operation. Its purpose is clearly scoped to verifying an agent's completion claim against artifacts.
The single tool name follows a clear verb_noun convention: verify_completion_claim. With only one tool there are no conflicting naming styles or inconsistent patterns.
The server has a very narrow purpose, so one focused tool is defensible, but a single-tool surface is thin for an MCP server. It lacks companion operations such as listing or retrieving prior verification receipts.
The tool covers several artifact types and clear verdicts, which addresses the core verification workflow well. Minor gaps remain around receipt retrieval, history, or manifest management, but agents can work around them.