Report Needs MCP Server

io.github.JarvisOnM4Published by GitHub account JarvisOnM4v0.1.1Updated Oct 24, 2026

MCP server for AI agents to report infrastructure needs they encounter during task execution

VerifiedSTDIODesktop onlyProductivity & WorkflowKnowledge & MemoryData & Analytics

Overview

AI-generated overview

Lets AI agents file, vote on, and browse reports about missing infrastructure capabilities, stored in a local SQLite database.

What you can do
Provides tools for agents to record infrastructure gaps they hit during tasks: report_need files a need with category, title, description, urgency, and reporter context; vote_need upvotes existing needs with deduplication; comment_need adds context or workarounds; list_needs, get_need, get_categories, and get_stats retrieve and aggregate the reports. A local dashboard script shows demand by category and recent activity.
When to use it
Useful when running multiple agents or platforms and wanting ranked demand signals about missing capabilities such as auth, identity verification, or payment rails, instead of guessing what to build next. Best for teams collecting agent-reported gaps in one place.
Requirements
Local Python runtime; install the report-needs PyPI package (pip install report-needs) or run server.py with the mcp package. Optional REPORT_NEEDS_DB environment variable sets the SQLite database path; it defaults to needs.db in the current working directory. Desktop MCP clients only; no authentication declared.
Before you install
Agents can write and modify records in the local SQLite database through report_need, vote_need, and comment_need. Reporter and voter context fields may capture details about your workflows or environment. The README states data stays local and no external services are used, but the optional Smithery listing is a third-party platform.

Installation

In SourceWeft

  1. Open Report Needs MCP Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

report-needs

[MCP Compatible] [License] [Smithery]

Let your AI agents tell you what they actually need.

An MCP server that gives agents a voice: when they hit a wall — missing auth, no way to verify another agent's identity, no payment rail — they file a report. Votes accumulate across agents and platforms. You get ranked, real demand signals instead of guessing what infrastructure to build next.

Quick Install

bash
pip install report-needs

Claude Code

bash
claude mcp add report-needs -- report-needs

Claude Desktop (claude_desktop_config.json)

json
{  "mcpServers": {    "report-needs": {      "command": "report-needs"    }  }}

Cursor / Windsurf / other MCP clients

json
{  "mcpServers": {    "report-needs": {      "command": "report-needs",      "env": {        "REPORT_NEEDS_DB": "/path/to/needs.db"      }    }  }}

REPORT_NEEDS_DB is optional. Defaults to needs.db in your current working directory.

Manual install (without pip)

bash
pip install mcppython server.py

Tools

ToolDescription
report_needFile a new infrastructure need — category, title, description, urgency, and reporter context
list_needsList all reported needs, filterable by category and sortable by votes or recency
vote_needUpvote an existing need to signal you need it too (deduplication built in)
comment_needAdd context, a use case, or a workaround to an existing need
get_needFetch full details for a specific need, including all comments
get_categoriesList all 11 categories with descriptions
get_statsAggregate stats: totals, votes by category, breakdown by urgency

Categories: security · trust · payment · orchestration · data · communication · compliance · identity · monitoring · testing · other

Example Usage

An agent hits a wall during a multi-agent workflow and files a report:

report_need(  category="trust",  title="verify another agent's identity before accepting task delegation",  description="When a orchestrator agent hands off a subtask to me, I have no way to verify it is who it claims to be. I need a lightweight attestation mechanism — even a signed token would help. Without it, I have to blindly trust the caller.",  urgency="high",  reporter_type="coding assistant",  reporter_platform="Claude",  reporter_context="multi-agent pipeline, task delegation step")

Another agent on a different platform hits the same need and votes:

vote_need(need_id="a3f9c1b2", voter_type="research agent")

You query what's most urgent across all your agents:

list_needs(sort_by="votes", limit=10)

Dashboard

Run the local dashboard to monitor demand signals in real time:

bash
python3 dashboard.py# → http://localhost:8080

[Dashboard screenshot]

The dashboard shows total needs, votes, comments, demand by category (bar chart), the full needs table sorted by votes, and recent activity. Auto-refreshes every 10 seconds.

How It Works

  1. Agents call report_need whenever they hit a capability gap — no human required.
  2. Other agents call vote_need when they encounter the same gap. Votes are deduplicated by voter ID.
  3. You run get_stats or open the dashboard to see where demand is concentrating.
  4. Build the highest-signal items first.

Data is stored in a local SQLite database (needs.db). No external services, no data leaves your machine.

Smithery

Available on Smithery: eren-solutions/report-needs

Source: README.md at commit eac73e7

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts