# writ (pypi · writ-mcp)

Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log.

- Trust score: 54/100 (low)
- Change this week: −7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `writ-mcp`: 54/100 (this document), [markdown](https://verifymcp.io/servers/avenuedadmin-writ/writ-mcp.md), [page](https://verifymcp.io/servers/avenuedadmin-writ/writ-mcp)

## Channel facts

- Registry: `pypi`
- Package: `writ-mcp`
- Version: `0.1.2`
- 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 2026-10-18.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 0 of 28 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL redirects; it must resolve directly.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 16 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 73/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 865 tokens (~108/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 57/100
  - Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "writ_revoke" implies "revoke" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

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

writ runs locally as a PyPI package, launched with uvx writ-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 avenuedadmin-writ -- uvx writ-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "avenuedadmin-writ": {
      "command": "uvx",
      "args": [
        "writ-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "avenuedadmin-writ": {
      "command": "uvx",
      "args": [
        "writ-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add avenuedadmin-writ -- uvx writ-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "avenuedadmin-writ": {
      "type": "local",
      "command": [
        "uvx",
        "writ-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add avenuedadmin-writ --command uvx --arg writ-mcp
```

### Hermes

```yaml
mcp_servers:
  avenuedadmin-writ:
    command: "uvx"
    args: ["writ-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "avenuedadmin-writ": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "writ-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add avenuedadmin-writ -t stdio -c uvx -a writ-mcp
```

### Other

```json
{
  "mcpServers": {
    "avenuedadmin-writ": {
      "command": "uvx",
      "args": [
        "writ-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.

### 2026-10-18 (score 54, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-17 (score 69, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-16 (score 53, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-15 (score 68, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-14 (score 52, −15)

- [security regression] Malware scan: pass → unverified

### 2026-10-13 (score 67, +6)

- [functional improvement] Stability: unverified → 0.40

### 2026-10-02 (score 61, −5)

- [security regression] Source repository: pass → fail

### 2026-10-01 (score 66)

First indexed and scored.

## MCP tools (8)

### `writ_check` (~313 tokens)

Ask Writ whether an action may proceed. CALL THIS BEFORE any consequential write.

A consequential write is anything hard to undo: sending money or messages,
changing access or identity records, deleting data, calling an external API
that acts in the world.

Args:
    sponsor_id: The human sponsor accountable for this action (e.g. a user id or email).
    agent_id:   The agent or workflow performing the action.
    verb:       What is being done (e.g. "verify_human", "send_payment").
    target:     What it acts on (e.g. "benefit-case-123").
    purpose:    Why, in plain words. Be specific — the approval is bound to this purpose.

Returns a decision:
  ALLOW   — proceed. You get an authToken valid 90 seconds, bound to this
            exact sponsor/agent/verb/target/purpose. Call writ_verify_token
            against the intended write immediately before executing it.
  DENY    — do NOT perform the action. Explain the receipt reason to the user.
  STEP_UP — a human sponsor must approve first. Tell the user what needs
            approval; they can approve via writ_grant (or the dashboard),
            then call writ_check again.
Every outcome creates an audit receipt with a receiptId.

Input parameters:

- `agent_id` (string, required)
- `purpose` (string, required)
- `sponsor_id` (string, required)
- `target` (string, required)
- `verb` (string, required)

Output parameters:

- `result` (string)

### `writ_verify_token` (~135 tokens)

Verify a Writ auth token against the write you are about to execute.

Call this IMMEDIATELY before executing an ALLOWed write, with the exact
verb/target/purpose you intend. If valid is false — expired, tampered, or
bound to a different purpose — do NOT execute the write; call writ_check again.

This is the commit-time enforcement: the check authorizes, the token proves
the authorization still matches what you are actually doing.

Input parameters:

- `auth_token` (string, required)
- `purpose` (string, required)
- `target` (string, required)
- `verb` (string, required)

Output parameters:

- `result` (string)

### `writ_grant` (~116 tokens)

SPONSOR ONLY. Mint a one-time grant approving a specific action.

Use this when writ_check returned STEP_UP and the human sponsor approves.
The grant is single-use: the next writ_check consumes it and returns ALLOW.
The grant is scoped to your tenant. Requires WRIT_SPONSOR_TOKEN.

Input parameters:

- `agent_id` (string, required)
- `purpose` (string, required)
- `sponsor_id` (string, required)
- `target` (string, required)
- `ttl_seconds` (integer)
- `verb` (string, required)

Output parameters:

- `result` (string)

### `writ_revoke` (~84 tokens)

SPONSOR ONLY. Kill switch: immediately deny all future checks for this principal.

Revocation overrides live grants and tenant policy. Use when a principal is
compromised, misbehaving, or its task is done. Scoped to your tenant.
Requires WRIT_SPONSOR_TOKEN.

Input parameters:

- `agent_id` (string, required)
- `sponsor_id` (string, required)

Output parameters:

- `result` (string)

### `writ_reinstate` (~57 tokens)

SPONSOR ONLY. Undo writ_revoke: the principal is evaluated by policy again.

Scoped to your tenant. Requires WRIT_SPONSOR_TOKEN.

Input parameters:

- `agent_id` (string, required)
- `sponsor_id` (string, required)

Output parameters:

- `result` (string)

### `writ_receipts` (~28 tokens)

List recent decision receipts (audit trail). Newest first.

Input parameters:

- `limit` (integer)

Output parameters:

- `result` (string)

### `writ_policy` (~29 tokens)

Read the tenant's verb policy: which verbs allow, deny, require a grant, or step up.

Output parameters:

- `result` (string)

### `writ_sandbox` (~103 tokens)

Get a free 90-second sandbox grant for a demo write. No API key needed.

Issues a live grant for verb "demo_write" on a target starting with "demo-",
then runs writ_check so you get back an ALLOW decision plus auth token to
practice the verify-before-write flow end to end.

Input parameters:

- `agent_id` (string, required)
- `purpose` (string, required)
- `sponsor_id` (string, required)
- `target` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

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

## Score history

- 2026-10-18: 54
- 2026-10-17: 69
- 2026-10-16: 53
- 2026-10-15: 68
- 2026-10-14: 52
- 2026-10-13: 67
- 2026-10-12: 61
- 2026-10-04: 61
- 2026-10-03: 61
- 2026-10-02: 61
- 2026-10-01: 66

## Common questions

### What is the writ MCP server?

writ is an MCP server listed in the public MCP registry as io.github.AvenueDAdmin/writ. Commit-time policy checks for AI agent writes (ALLOW/DENY/STEP_UP) with a tamper-evident audit log. This page covers its PyPI package (writ-mcp).

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

writ scores 54 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. 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 writ MCP server expose?

writ exposes 8 tools: writ_check, writ_verify_token, writ_grant, writ_revoke, writ_reinstate, and 3 more. Their descriptions and schemas cost roughly 865 tokens of context every time the server is loaded.

### Is the writ MCP server still maintained?

writ is still listed as active in the MCP registry. We last reached this channel on 18 October 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 writ MCP server under?

writ 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

- PyPI project: https://pypi.org/project/writ-mcp/
- Socket report: https://socket.dev/pypi/package/writ-mcp
- Website: https://withwrit.com/
- Changelog RSS feed: https://verifymcp.io/servers/avenuedadmin-writ/writ-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/avenuedadmin-writ/writ-mcp.json
- HTML version of this page: https://verifymcp.io/servers/avenuedadmin-writ/writ-mcp