# throng (npm · throng-mcp)

Hands work to another coding agent over ACP: Claude Code, Codex, OpenCode, Gemini CLI and others

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `throng-mcp`: 87/100 (this document), [markdown](https://verifymcp.io/servers/agent-runbooks-throng-mcp/throng-mcp.md), [page](https://verifymcp.io/servers/agent-runbooks-throng-mcp/throng-mcp)

## Channel facts

- Registry: `npm`
- Package: `throng-mcp`
- Version: `0.9.1`
- 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 2026-11-21.

- **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.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to agent-runbooks/throng-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 12 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 936 tokens (~156/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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.
  - All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.
  - An AI judge read all 6 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 throng MCP server?

throng runs locally as an npm package, launched with npx -y throng-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 agent-runbooks-throng-mcp -- npx -y throng-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "agent-runbooks-throng-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "throng-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "agent-runbooks-throng-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "throng-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add agent-runbooks-throng-mcp -- npx -y throng-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add agent-runbooks-throng-mcp --command npx --arg -y --arg throng-mcp
```

### Hermes

```yaml
mcp_servers:
  agent-runbooks-throng-mcp:
    command: "npx"
    args: ["-y", "throng-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "agent-runbooks-throng-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "throng-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add agent-runbooks-throng-mcp -t stdio -c npx -a -y throng-mcp
```

### Other

```json
{
  "mcpServers": {
    "agent-runbooks-throng-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "throng-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.

### 2026-11-20 (score 87, +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.

### 2026-11-18 (score 86, +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.

### 2026-11-15 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-13 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-09 (score 82, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-08 (score 66, 0)

- [security improvement] Malware scan: unverified → pass
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.9.0 → 0.9.1

### 2026-11-07 (score 66)

First indexed and scored.

## MCP tools (6)

### `cancel_thronglet` (~73 tokens)

Cancels the session's running turn (session/cancel) and drops its queued messages; a pending wait_thronglet returns the cancelled error. The session is idle afterwards and accepts a new send_message. No-op on an idle session.

Input parameters:

- `session_id` (string, required): session_id from run_thronglet

### `list_harnesses` (~58 tokens)

Lists valid agent values for run_thronglet: installed harnesses with their models and effort levels, installed or configured ones that cannot run with the reason, and the server limits. Built-in harnesses that are not installed are not listed.

### `list_thronglets` (~76 tokens)

Lists thronglet sessions on this machine: description, agent, cwd, state (running | queued | idle | failed), queue length, accepts_messages (false: send_message to it fails), timestamps and the last error. Live state is this server's; a session run by another throng instance shows what its record says.

### `run_thronglet` (~298 tokens)

Runs an agent of an installed harness (see list_harnesses) on a task in cwd and returns its final message as JSON {session_id, text, stop_reason, usage, duration_s, warnings?}; with schema, structured replaces text. description names the thronglet for listings. With background: true the call returns {session_id, state, queued} as soon as the turn runs; collect the result with wait_thronglet.

Input parameters:

- `agent` (string, required): <harness>/<model>[:<effort>], e.g. claude/opus:max, codex/gpt-6-sol:xhigh; valid values: list_harnesses
- `background` (boolean): Return as soon as the turn is running (or queued behind the session's current turn); collect the result with wait_thronglet
- `cwd` (string, required): Absolute path; the agent works in this tree
- `description` (string, required): What this thronglet is for, in a few words; shown in session listings
- `prompt` (string, required): Task for the agent
- `schema` (object): JSON Schema (draft-07 or 2020-12) for structured output: the agent ends with a matching JSON value as its final message, returned as `structured` instead of `text`
- `timeout_s` (number): Wall-clock limit for the run in seconds; default from config (21600)

### `send_message` (~315 tokens)

Sends the next message into an earlier session (session_id from run_thronglet) and returns the same JSON as run_thronglet. A message to a session whose turn is still running waits for that turn to end: turns on one session never overlap. With background: true the call returns {session_id, state, queued} as soon as the turn runs; collect the result with wait_thronglet. steer: true interrupts the running turn and delivers this message next; queued messages follow it. A session its harness cannot continue (resume or load) takes no further message, steer included: list_thronglets shows it as accepts_messages: false.

Input parameters:

- `background` (boolean): Return as soon as the turn is running (or queued behind the session's current turn); collect the result with wait_thronglet
- `prompt` (string, required): Next message for the agent
- `schema` (object): JSON Schema (draft-07 or 2020-12) for structured output: the agent ends with a matching JSON value as its final message, returned as `structured` instead of `text`
- `session_id` (string, required): session_id from run_thronglet
- `steer` (boolean): Interrupt the running turn (session/cancel) and run this message as the very next turn, ahead of queued messages. The in-flight tool call is aborted; a half-applied edit may remain.
- `timeout_s` (number): Wall-clock limit for the run in seconds; default from config (21600)

### `wait_thronglet` (~116 tokens)

Waits until a session has no running or queued turn and returns the last turn's result: the same JSON as run_thronglet, or its error. With timeout_s elapsed returns {session_id, state, queued} instead. Idempotent: the result is stored with the session.

Input parameters:

- `session_id` (string, required): session_id from run_thronglet
- `timeout_s` (number): How long to wait in seconds; default from config (21600). Elapsed → the session state, not an error

## Diagnostics

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

## Score history

- 2026-11-21: 87
- 2026-11-20: 87
- 2026-11-19: 86
- 2026-11-18: 86
- 2026-11-17: 85
- 2026-11-16: 85
- 2026-11-15: 85
- 2026-11-14: 84
- 2026-11-13: 84
- 2026-11-12: 83
- 2026-11-11: 83
- 2026-11-10: 82
- 2026-11-09: 82
- 2026-11-08: 66
- 2026-11-07: 66

## Common questions

### What is the throng MCP server?

throng is an MCP server listed in the public MCP registry as io.github.agent-runbooks/throng-mcp. Hands work to another coding agent over ACP: Claude Code, Codex, OpenCode, Gemini CLI and others. This page covers its npm package (throng-mcp).

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

throng scores 87 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 throng MCP server expose?

throng exposes 6 tools: cancel_thronglet, list_harnesses, list_thronglets, run_thronglet, send_message, wait_thronglet. Their descriptions and schemas cost roughly 936 tokens of context every time the server is loaded.

### Is the throng MCP server still maintained?

throng is still listed as active in the MCP registry. We last reached this channel on 21 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 throng MCP server under?

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

### What did VerifyMCP test on the throng MCP server?

VerifyMCP ran 16 checks on throng, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/throng-mcp
- Socket report: https://socket.dev/npm/package/throng-mcp
- Repository: https://github.com/agent-runbooks/throng-mcp
- Changelog RSS feed: https://verifymcp.io/servers/agent-runbooks-throng-mcp/throng-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/agent-runbooks-throng-mcp/throng-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/agent-runbooks-throng-mcp/throng-mcp.json
- HTML version of this page: https://verifymcp.io/servers/agent-runbooks-throng-mcp/throng-mcp
