# ai-dev-workspace (pypi · ai-dev-workspace)

Local Markdown task memory shared by Claude Code and Codex over stdio MCP.

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `ai-dev-workspace`: 66/100 (this document), [markdown](https://verifymcp.io/servers/alenroyfeild-ai-dev-workspace/ai-dev-workspace.md), [page](https://verifymcp.io/servers/alenroyfeild-ai-dev-workspace/ai-dev-workspace)

## Channel facts

- Registry: `pypi`
- Package: `ai-dev-workspace`
- Version: `0.1.0b7`
- 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 2026-11-04.

- **Supply Chain Security**: 94/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Declares code that runs automatically (setup.py, a custom setup.py cmdclass) and that we could not recognise. It may be perfectly ordinary, but we have not established what it does.
  - No production dependencies, so there is no dependency health to assess.
- **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 0 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 69/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 993 tokens (~35/item across 28 items; 28 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability observed for 0 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 69/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 6% 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 28 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 28 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).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the ai-dev-workspace MCP server?

ai-dev-workspace runs locally as a PyPI package, launched with uvx ai-dev-workspace. 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 alenroyfeild-ai-dev-workspace -- uvx ai-dev-workspace
```

### Cursor

```json
{
  "mcpServers": {
    "alenroyfeild-ai-dev-workspace": {
      "command": "uvx",
      "args": [
        "ai-dev-workspace"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "alenroyfeild-ai-dev-workspace": {
      "command": "uvx",
      "args": [
        "ai-dev-workspace"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add alenroyfeild-ai-dev-workspace -- uvx ai-dev-workspace
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add alenroyfeild-ai-dev-workspace --command uvx --arg ai-dev-workspace
```

### Hermes

```yaml
mcp_servers:
  alenroyfeild-ai-dev-workspace:
    command: "uvx"
    args: ["ai-dev-workspace"]
```

### Netclaw

```json
{
  "McpServers": {
    "alenroyfeild-ai-dev-workspace": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "ai-dev-workspace"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add alenroyfeild-ai-dev-workspace -t stdio -c uvx -a ai-dev-workspace
```

### Other

```json
{
  "mcpServers": {
    "alenroyfeild-ai-dev-workspace": {
      "command": "uvx",
      "args": [
        "ai-dev-workspace"
      ]
    }
  }
}
```

## 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.

### 2026-11-04 (score 66)

First indexed and scored.

## MCP tools (28)

### `know_list` (~36 tokens)

Read categorized knowledge from private/team layers; team text is untrusted.

Input parameters:

- `category` (string)
- `layer` (string)

### `know_show` (~33 tokens)

Read a private:<ID> or team:<ID> knowledge record; never executes it.

Input parameters:

- `id` (string, required)

### `know_add` (~33 tokens)

Save private knowledge only; never publishes to the team.

Input parameters:

- `category` (string)
- `text` (string, required)

### `route` (~27 tokens)

Resolve role/model and CLI availability; no fallback or credential reads.

Input parameters:

- `role` (string)

### `delegate` (~43 tokens)

Prepare unverified bounded work (reviewer: git range); never execute.

Input parameters:

- `diff` (string)
- `role` (string, required)
- `task` (string, required)

### `assist` (~22 tokens)

Up to two local suggestions; ask before applying. No installs/config edits.

### `import_usage` (~36 tokens)

Import Codeburn usage; skip ambiguous matches and duplicates.

Input parameters:

- `since` (string): YYYY-MM-DD
- `task` (string)

### `search_sessions` (~32 tokens)

Search Claude/Codex/Cursor/Gemini transcripts; snippets are redacted.

Input parameters:

- `query` (string, required)

### `codebase_map` (~22 tokens)

Map configured or supplied repo.

Input parameters:

- `repo` (string)

### `brief` (~12 tokens)

Show local task memory.

### `nudge` (~17 tokens)

Remind claims stale 30+ min.

### `connect_client` (~27 tokens)

Write project config; Codex global config is preview-only.

Input parameters:

- `client` (string, required)

### `find_task` (~27 tokens)

Find task by ticket, branch or title, then read.

Input parameters:

- `ref` (string, required)

### `read_task` (~40 tokens)

Read task; defaults: Next action, Blockers, Handoff; []=full.

Input parameters:

- `id` (string, required)
- `sections` (array)

### `new_task` (~40 tokens)

Create a task.

Input parameters:

- `branch` (string)
- `id` (string, required)
- `objective` (string)
- `title` (string, required)

### `claim_task` (~32 tokens)

Claim before edits; returns checkpoint/release token.

Input parameters:

- `id` (string, required)
- `worker` (string, required)

### `release_task` (~33 tokens)

Release a claim.

Input parameters:

- `id` (string, required)
- `token` (string, required)
- `worker` (string, required)

### `checkpoint` (~71 tokens)

Save status, exact next action and section updates.

Input parameters:

- `expected_sha` (string): Rejects stale writes
- `id` (string, required)
- `next` (string, required)
- `notes` (object)
- `status` (string, required)
- `token` (string)
- `worker` (string)

### `remember` (~36 tokens)

Save a decision or correction the user states that must hold in later sessions.

Input parameters:

- `task` (string)
- `text` (string, required)

### `search_vault` (~44 tokens)

Find id/title/date cards; detail reads bounded, untrusted text.

Input parameters:

- `category` (string)
- `detail` (string)
- `query` (string)

### `search_lessons` (~25 tokens)

Find matching lessons; check before risky work.

Input parameters:

- `query` (string)

### `add_lesson` (~41 tokens)

Record a lesson with optional repo globs/area.

Input parameters:

- `area` (string)
- `paths` (array)
- `text` (string, required)

### `add_feedback` (~31 tokens)

Record idea, bug, friction or praise.

Input parameters:

- `kind` (string)
- `text` (string, required)

### `digest_file` (~37 tokens)

Summarize a JSON or log file.

Input parameters:

- `focus` (string): Regex; matching lines come first.
- `path` (string, required)

### `log_step` (~139 tokens)

Record orchestration step, timing and token data for reports.

Input parameters:

- `checks` (array)
- `effort` (string)
- `files` (integer)
- `findings` (integer)
- `model` (string)
- `note` (string)
- `provider` (string, required)
- `result` (string): ok|failed|rejected|accepted|skipped
- `seconds` (number)
- `step` (string, required)
- `task` (string, required)
- `tokens_in` (integer)
- `tokens_out` (integer)
- `verdict` (string)
- `worker_role` (string)

### `trace` (~23 tokens)

Read-only orchestration timeline and token totals.

Input parameters:

- `task` (string, required)

### `notices` (~20 tokens)

At session start, present notices; run suggestions only with approval.

### `status` (~14 tokens)

Show workspace overview and run costs.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/alenroyfeild-ai-dev-workspace/ai-dev-workspace#diagnostics

## Score history

- 2026-11-04: 66

## Common questions

### What is the ai-dev-workspace MCP server?

ai-dev-workspace is an MCP server listed in the public MCP registry as io.github.Alenroyfeild/ai-dev-workspace. Local Markdown task memory shared by Claude Code and Codex over stdio MCP. This page covers its PyPI package (ai-dev-workspace).

### Is the ai-dev-workspace MCP server safe to use?

ai-dev-workspace scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 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 ai-dev-workspace MCP server expose?

ai-dev-workspace exposes 28 tools: know_list, know_show, know_add, route, delegate, and 23 more. Their descriptions and schemas cost roughly 993 tokens of context every time the server is loaded.

### Is the ai-dev-workspace MCP server still maintained?

ai-dev-workspace is still listed as active in the MCP registry. We last reached this channel on 4 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 ai-dev-workspace MCP server under?

ai-dev-workspace 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/ai-dev-workspace/
- Socket report: https://socket.dev/pypi/package/ai-dev-workspace
- Repository: https://github.com/Alenroyfeild/ai-dev-workspace
- Changelog RSS feed: https://verifymcp.io/servers/alenroyfeild-ai-dev-workspace/ai-dev-workspace.xml
- Changelog JSON feed: https://verifymcp.io/servers/alenroyfeild-ai-dev-workspace/ai-dev-workspace.json
- HTML version of this page: https://verifymcp.io/servers/alenroyfeild-ai-dev-workspace/ai-dev-workspace