# CONTRI (npm · contri-mcp)

Is this GitHub issue free to take, is the project alive, will maintainers reply? Read-only.

- Trust score: 75/100 (medium)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `contri-mcp`: 75/100 (this document), [markdown](https://verifymcp.io/servers/alphasafal-contri/contri-mcp.md), [page](https://verifymcp.io/servers/alphasafal-contri/contri-mcp)

## Channel facts

- Registry: `npm`
- Package: `contri-mcp`
- Version: `0.2.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 78/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1174 tokens (~130/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 96/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 89% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the CONTRI MCP server?

CONTRI runs locally as an npm package, launched with npx -y contri-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add alphasafal-contri -- npx -y contri-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "alphasafal-contri": {
      "command": "npx",
      "args": [
        "-y",
        "contri-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "alphasafal-contri": {
      "command": "npx",
      "args": [
        "-y",
        "contri-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add alphasafal-contri -- npx -y contri-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "alphasafal-contri": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "contri-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add alphasafal-contri --command npx --arg -y --arg contri-mcp
```

### Hermes

```yaml
mcp_servers:
  alphasafal-contri:
    command: "npx"
    args: ["-y", "contri-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "alphasafal-contri": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "contri-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add alphasafal-contri -t stdio -c npx -a -y contri-mcp
```

### Other

```json
{
  "mcpServers": {
    "alphasafal-contri": {
      "command": "npx",
      "args": [
        "-y",
        "contri-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 73, +2)

- [functional improvement] Stability: unverified → 0.10

### 2026-10-30 (score 71, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-29 (score 56)

First indexed and scored.

## MCP tools (9)

### `check_issue` (~151 tokens)

Can I take this issue?

Is this issue free to take? One verdict (Looks free, Claimed by @x, Claim went quiet, Open PR #n, Assigned, Closed, Partly checked) from assignees, claim comments and referencing PRs, with evidence links. 1–2 requests signed in, ~4 anonymous.

Input parameters:

- `detail` (string): brief: verdict + URL (~40 tokens); full: with evidence
- `force` (boolean): Bypass the cache (costs requests)
- `includeThread` (boolean): Also return issue text and recent comments (up to ~14k chars)
- `issue` (string, required): https://github.com/owner/name/issues/123 or owner/name#123

### `check_issues` (~74 tokens)

Can I take any of these issues?

check_issue for up to 10 issues in one call, verdicts only by default. Same cost per issue.

Input parameters:

- `detail` (string): brief: verdict + URL (~40 tokens); full: with evidence
- `force` (boolean): Bypass the cache (costs requests)
- `issues` (array, required)

### `repo_health` (~82 tokens)

Is this project alive?

Is the project alive? PRs merged in 90 days (bots excluded), human authors, commits, weekly merges, median time to merge, open counts, latest release. 2 requests signed in, ~7 anonymous.

Input parameters:

- `force` (boolean): Bypass the cache (costs requests)
- `repo` (string, required): owner/name or a github.com URL

### `team_responsiveness` (~94 tokens)

Will a maintainer reply?

Will a maintainer reply? Median first team reply to outside PRs and issues, who is still waiting, and the maintainer roster. Call once per repository before check_issue: it improves claim detection. 2–3 requests signed in, up to ~35 anonymous.

Input parameters:

- `force` (boolean): Bypass the cache (costs requests)
- `repo` (string, required): owner/name or a github.com URL

### `find_issues` (~141 tokens)

Find issues to take

Open issues in one repository, newest activity first; defaults to beginner labels without an assignee. Comment claims are not checked: confirm with check_issue(s). 3 requests signed in, 2 anonymous.

Input parameters:

- `force` (boolean): Bypass the cache (costs requests)
- `label` (string): default beginner = good first issue or help wanted
- `limit` (integer): default 10
- `page` (integer)
- `query` (string): Search words (no qualifiers)
- `repo` (string, required): owner/name or a github.com URL
- `sort` (string)
- `unassigned` (boolean): default true

### `discover_projects` (~100 tokens)

Discover projects

Active public projects ranked by recent human merges and open good-first-issues, by language or topic. 1 request per language signed in, ~7 anonymous.

Input parameters:

- `force` (boolean): Bypass the cache (costs requests)
- `language` (string): e.g. TypeScript, Python, Rust
- `personalize` (boolean): Match the signed-in user's languages
- `query` (string): Topic words, e.g. cli, accessibility

### `contribution_brief` (~95 tokens)

Contribution brief

A source-linked brief for one issue plus links to the project's README, contributing guide, code of conduct and templates. One request more than check_issue.

Input parameters:

- `force` (boolean): Bypass the cache (costs requests)
- `issue` (string, required): https://github.com/owner/name/issues/123 or owner/name#123
- `task` (string): plan (default), explain, or review (self-review checklist)

### `sign_in` (~75 tokens)

Sign in with GitHub

GitHub device-flow sign-in (60 → 5,000 requests an hour, public read-only, no scopes). Ask the user first. Show the returned code and link exactly; CONTRI notices the approval by itself. Call again to check.

Input parameters:

- `remember` (boolean): Keep the sign-in on this computer (default true)

### `sign_out` (~33 tokens)

Sign out of GitHub

Forgets the sign_in credential, including the saved copy. A GITHUB_TOKEN in the MCP config must be removed there.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/alphasafal-contri/contri-mcp#diagnostics

## Score history

- 2026-11-05: 75
- 2026-11-04: 74
- 2026-11-03: 74
- 2026-11-02: 73
- 2026-11-01: 73
- 2026-10-31: 71
- 2026-10-30: 71
- 2026-10-29: 56

## Common questions

### What is the CONTRI MCP server?

CONTRI is an MCP server listed in the public MCP registry as io.github.alphasafal/contri. Is this GitHub issue free to take, is the project alive, will maintainers reply? Read-only. This page covers its npm package (contri-mcp).

### Is the CONTRI MCP server safe to use?

CONTRI scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CONTRI MCP server expose?

CONTRI exposes 9 tools: check_issue, check_issues, repo_health, team_responsiveness, find_issues, and 4 more. Their descriptions and schemas cost roughly 845 tokens of context every time the server is loaded.

### Is the CONTRI MCP server still maintained?

CONTRI is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the CONTRI MCP server under?

CONTRI declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/contri-mcp
- Socket report: https://socket.dev/npm/package/contri-mcp
- Repository: https://github.com/alphasafal/contri
- Website: https://contri-two.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/alphasafal-contri/contri-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/alphasafal-contri/contri-mcp.json
- HTML version of this page: https://verifymcp.io/servers/alphasafal-contri/contri-mcp