# ClawPipe (npm · clawpipe-mcp-server)

Cost-optimized LLM pipeline + 6 AI security skills (reasoning, triage, remediation, compliance).

- Trust score: 55/100 (low)
- Change this week: +18
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `clawpipe-mcp-server`: 55/100 (this document), [markdown](https://verifymcp.io/servers/finsavvyai-clawpipe-mcp-server/clawpipe-mcp-server.md), [page](https://verifymcp.io/servers/finsavvyai-clawpipe-mcp-server/clawpipe-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `clawpipe-mcp-server`
- Version: `3.2.0`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 105 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 60/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 555 tokens (~46/item across 12 items; 12 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 76/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 29% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 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

### Claude

```bash
claude mcp add finsavvyai-clawpipe-mcp-server -- npx -y clawpipe-mcp-server
```

### Codex

```bash
codex mcp add finsavvyai-clawpipe-mcp-server -- npx -y clawpipe-mcp-server
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add finsavvyai-clawpipe-mcp-server --command npx --arg -y --arg clawpipe-mcp-server
```

### Hermes

```yaml
mcp_servers:
  finsavvyai-clawpipe-mcp-server:
    command: "npx"
    args: ["-y", "clawpipe-mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "finsavvyai-clawpipe-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "clawpipe-mcp-server"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 55, +42)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] License: unverified → pass
- [functional improvement] Schema quality: unverified → fair
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 13, +13)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 0, −19)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 19, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 37)

First indexed and scored.

## MCP tools (12)

### `clawpipe_prompt` (~102 tokens)

Send a prompt through the ClawPipe pipeline (Booster -> Pack -> Cache -> Route -> Call -> Learn). Returns the response text and pipeline metadata.

Input parameters:

- `model` (string): Override model selection (e.g. gpt-4o)
- `prompt` (string, required): The prompt text to send through the pipeline
- `provider` (string): Override provider (e.g. openai, anthropic)
- `system` (string): Optional system message

### `clawpipe_analyze_cost` (~51 tokens)

Estimate the cost of a prompt without sending it. Shows token count, estimated cost per model, and potential savings from Booster and Packer.

Input parameters:

- `prompt` (string, required): The prompt text to analyze

### `clawpipe_stats` (~32 tokens)

Get current session telemetry: total requests, tokens, cost, cache hit rate, top models, and average latency.

### `clawpipe_booster_check` (~60 tokens)

Check if a prompt can be resolved by the Agent Booster without calling an LLM. Returns the result if resolvable, or indicates that an LLM call is needed.

Input parameters:

- `prompt` (string, required): The prompt to check against booster rules

### `clawpipe_report_to_jira` (~66 tokens)

Create a Jira issue. Use for budget breaches, cost spikes, or agent anomalies.

Input parameters:

- `description` (string, required)
- `issue_type` (string)
- `project_key` (string, required)
- `severity` (string)
- `summary` (string, required)

### `clawpipe_report_to_notion` (~64 tokens)

Append a page to a Notion database. Use for cost digests, weekly summaries, incident logs.

Input parameters:

- `body_markdown` (string)
- `database_id` (string, required)
- `properties` (object)
- `title` (string, required)

### `clawpipe_skill_reasoning` (~28 tokens)

Root-cause + risk-score a security finding.

Input parameters:

- `input` (string, required)

### `clawpipe_skill_triage` (~29 tokens)

Prioritize a batch of security findings by actual risk.

Input parameters:

- `input` (string, required)

### `clawpipe_skill_remediation` (~27 tokens)

Generate a fix plus rollback for a vulnerability.

Input parameters:

- `input` (string, required)

### `clawpipe_skill_compliance` (~34 tokens)

Write SOC 2 / ISO 27001 / HIPAA / GDPR evidence.

Input parameters:

- `input` (string, required)

### `clawpipe_skill_threat_intel` (~35 tokens)

Enrich CVE / IOC with NVD/CIRCL-style context.

Input parameters:

- `input` (string, required)

### `clawpipe_skill_incident` (~27 tokens)

Reconstruct attack chain + recommend containment steps.

Input parameters:

- `input` (string, required)

## Diagnostics

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

## Score history

- 2026-08-03: 55
- 2026-08-02: 55
- 2026-08-01: 13
- 2026-07-31: 0
- 2026-07-30: 19
- 2026-07-28: 37
- 2026-07-27: 37

## Links

- npm package: https://www.npmjs.com/package/clawpipe-mcp-server
- Socket report: https://socket.dev/npm/package/clawpipe-mcp-server
- Website: https://clawpipe.ai/
- Changelog RSS feed: https://verifymcp.io/servers/finsavvyai-clawpipe-mcp-server/clawpipe-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/finsavvyai-clawpipe-mcp-server/clawpipe-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/finsavvyai-clawpipe-mcp-server/clawpipe-mcp-server