gripe-mcp
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., "@gripe-mcp Log an issue: the 'plot' tool documentation is missing parameter descriptions."
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.
gripe-mcp
Agent complaint box — one-tool MCP for logging bugs and improvement requests.
One tool: report_issue
Call it when you guess, hit a missing tool, find bad docs, or produce uncertain output. Non-blocking — log and continue.
Param | Type | Description |
| str | What went wrong or what you'd like improved (max 200 chars) |
|
| low = friction, medium = guessed, high = abandoned/wrong |
| str | Which instruction or tool caused the issue (max 80 chars) |
| enum |
|
Related MCP server: agent-obs
Storage
Postgres: set
GRIPE_DB_URLenv var → singlegripe_issuestableJSONL fallback: timestamped files in
.gripe-mcp/(one per day)
Identity
GRIPE_AGENT_ID and GRIPE_TASK_ID are set at server startup via env vars.
The agent never self-reports identity.
System prompt block
## Self-Monitoring
Use `report_issue` any time you guess, hit a missing tool, or produce output
you're uncertain about. Non-blocking — log and continue, no response expected.
There is no penalty for logging; silence is the failure mode we're trying to
prevent.Run
GRIPE_AGENT_ID=precis GRIPE_TASK_ID=review-123 gripeAvailable Tools
1 toolreport_issueA
Report a bug, confusion, bad documentation, or improvement idea.
Call this when you:
had to guess or weren't confident in your output
hit a missing tool or capability
found unclear, wrong, or incomplete tool documentation
encountered ambiguous instructions
want to suggest a new tool, workflow step, or prompt fix
Non-blocking — log and continue your task. No response expected. There is no penalty for logging; silence is the failure mode.
description: what went wrong or what you'd like improved (max 200 chars) severity: low (friction) | medium (had to guess/workaround) | high (abandoned/wrong output) section: which instruction or tool caused the issue (max 80 chars) mode: ambiguous_instruction | missing_tool | bad_tool_doc | hallucination_risk | wrong_scope | memory_miss | other
Inputs: description (required), severity, section, mode. Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
Only one tool exists, so there is no possibility of confusion. The purpose is clearly distinct.
A single tool follows a clear verb_noun pattern (report_issue), so consistency is perfect.
With only one tool, the server feels very thin. Even for a focused reporting utility, a single tool is minimal and limits usefulness.
The tool covers its stated purpose (reporting issues) with detailed fields. For a single-purpose server, completeness is high, though there are no auxiliary tools.
Maintenance
Related MCP Connectors
Task and bug tracker for AI coding agents: 75 tools to file, triage and update work.
Issue tracker for coding agents: a real backlog, plus a risk-ranked review of every change.
Bug tracking for AI agents: session replay, console/network logs, repro packs, test plans, evidence.
Turn user requests and support messages into tasks and tell users what shipped, from any AI agent.
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceProvides tools for logging, confirming, and triaging issues with the semfora-engine, enabling AI agents to report bugs discovered during workflows.-- AlicenseNot gradedqualityCmaintenanceEnables AI agents to self-report every tool call, token usage, decision, and session grade into a local SQLite store, so users can trace execution, audit reasoning, and see per-session costs in a local dashboard. Also supports proxy mode to intercept and trace MCP tool invocations for agents that cannot self-report.79 npm2MIT
- AlicenseAqualityBmaintenanceLocal-first bug reports for coding agents: annotated screenshots, recordings and notes stored on your machine, served over MCP with the images included. Sync reports to GitHub issues when you choose.7MIT
- AlicenseAqualityBmaintenanceEnables AI coding agents to inspect annotated screenshots, user action steps, console errors, and failed network requests from bug reports, with tools, resources, and prompts for diagnosis and triage.2MIT