# io.github.youcisla/agent-foundry (pypi · agent-foundry-runtime)

Skill orchestrator: plan, execute, verify skills over MCP stdio.

- Trust score: 67/100 (medium)
- Change this week: +9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `agent-foundry-runtime`: 67/100 (this document), [markdown](https://verifymcp.io/servers/youcisla-agent-foundry/agent-foundry-runtime.md), [page](https://verifymcp.io/servers/youcisla-agent-foundry/agent-foundry-runtime)

## Channel facts

- Registry: `pypi`
- Package: `agent-foundry-runtime`
- Version: `0.4.2`
- 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 2026-11-04.

- **Supply Chain Security**: 91/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects filelock 3.32.7, reached via litellm > filelock. A fixed version is available.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 3 of 70 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 17 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 52/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 116 tokens (~29/item across 4 items; 4 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **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; "execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the io.github.youcisla/agent-foundry MCP server?

io.github.youcisla/agent-foundry runs locally as a PyPI package, launched with uvx agent-foundry-runtime. 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 youcisla-agent-foundry -- uvx agent-foundry-runtime
```

### Cursor

```json
{
  "mcpServers": {
    "youcisla-agent-foundry": {
      "command": "uvx",
      "args": [
        "agent-foundry-runtime"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "youcisla-agent-foundry": {
      "command": "uvx",
      "args": [
        "agent-foundry-runtime"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add youcisla-agent-foundry -- uvx agent-foundry-runtime
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add youcisla-agent-foundry --command uvx --arg agent-foundry-runtime
```

### Hermes

```yaml
mcp_servers:
  youcisla-agent-foundry:
    command: "uvx"
    args: ["agent-foundry-runtime"]
```

### Netclaw

```json
{
  "McpServers": {
    "youcisla-agent-foundry": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "agent-foundry-runtime"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add youcisla-agent-foundry -t stdio -c uvx -a agent-foundry-runtime
```

### Other

```json
{
  "mcpServers": {
    "youcisla-agent-foundry": {
      "command": "uvx",
      "args": [
        "agent-foundry-runtime"
      ]
    }
  }
}
```

## 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 67, +1)

- [functional improvement] Security disclosure: unverified → pass

### 2026-11-03 (score 66, +6)

- [security improvement] Source repository: fail → pass

### 2026-11-01 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 59, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 58, 0)

- [security regression] CVE-2026-112936 affects this package: high
- [security regression] CVE-2026-112939 affects this package: high
- [security regression] CVE-2026-112909 affects this package: high
- [security regression] CVE-2026-112910 affects this package: high
- [security regression] CVE-2026-112935 affects this package: high
- [security regression] CVE-2026-112908 affects this package: high
- [security regression] CVE-2026-112915 affects this package: high
- [security regression] CVE-2026-112911 affects this package: high
- [security regression] CVE-2026-112912 affects this package: high
- [security regression] CVE-2026-112938 affects this package: high

### 2026-10-28 (score 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 57, −1)

- [functional regression] Security disclosure: pass → unverified

### 2026-10-26 (score 58, −1)

- [security regression] Source repository: pass → fail
- [functional improvement] Stability: unverified → 0.30

## MCP tools (4)

### `plan` (~31 tokens)

Rank Agent Foundry skills for a prompt.

Input parameters:

- `max_results` (integer)
- `prompt` (string, required)

### `execute` (~41 tokens)

Run one skill against a prompt via the configured LLM.

Input parameters:

- `model` (string)
- `prompt` (string, required)
- `skill_id` (string, required)

### `list_skills` (~17 tokens)

List indexed skills with category and description.

### `get_skill` (~27 tokens)

Return the full SKILL.md body for one skill.

Input parameters:

- `skill_id` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/youcisla-agent-foundry/agent-foundry-runtime#diagnostics

## Score history

- 2026-11-04: 67
- 2026-11-03: 66
- 2026-11-02: 60
- 2026-11-01: 60
- 2026-10-31: 59
- 2026-10-30: 59
- 2026-10-29: 58
- 2026-10-28: 58
- 2026-10-27: 57
- 2026-10-26: 58
- 2026-10-25: 59
- 2026-10-24: 58
- 2026-10-23: 61
- 2026-10-22: 61
- 2026-10-21: 61
- 2026-10-20: 61
- 2026-10-19: 61
- 2026-10-18: 61
- 2026-10-17: 46

## Common questions

### What is the io.github.youcisla/agent-foundry MCP server?

io.github.youcisla/agent-foundry is an MCP server listed in the public MCP registry as io.github.youcisla/agent-foundry. Skill orchestrator: plan, execute, verify skills over MCP stdio. This page covers its PyPI package (agent-foundry-runtime).

### Is the io.github.youcisla/agent-foundry MCP server safe to use?

io.github.youcisla/agent-foundry scores 67 out of 100 on VerifyMCP. We recorded 13 known advisories against 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 io.github.youcisla/agent-foundry MCP server expose?

io.github.youcisla/agent-foundry exposes 4 tools: plan, execute, list_skills, get_skill. Their descriptions and schemas cost roughly 116 tokens of context every time the server is loaded.

### Is the io.github.youcisla/agent-foundry MCP server still maintained?

io.github.youcisla/agent-foundry 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 io.github.youcisla/agent-foundry MCP server under?

io.github.youcisla/agent-foundry 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/agent-foundry-runtime/
- Socket report: https://socket.dev/pypi/package/agent-foundry-runtime
- Repository: https://github.com/youcisla/Agent-Foundry
- Changelog RSS feed: https://verifymcp.io/servers/youcisla-agent-foundry/agent-foundry-runtime.xml
- Changelog JSON feed: https://verifymcp.io/servers/youcisla-agent-foundry/agent-foundry-runtime.json
- HTML version of this page: https://verifymcp.io/servers/youcisla-agent-foundry/agent-foundry-runtime