# ThinkerWave (pypi · thinkerwave-mcp)

Autonomous research agent for hard problems that labels every claim verified, assumption or guess.

- Trust score: 84/100 (high trust)
- Change this week: +19
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- pypi · `thinkerwave-mcp`: 84/100 (this document), [markdown](https://verifymcp.io/servers/thinkerwave-ai-thinkerwave/thinkerwave-mcp.md), [page](https://verifymcp.io/servers/thinkerwave-ai-thinkerwave/thinkerwave-mcp)

## Channel facts

- Registry: `pypi`
- Package: `thinkerwave-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 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 0 of 13 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to thinkerwave-ai/thinkerwave).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 15 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 58/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 417 tokens (~69/item across 6 items; 6 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 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 (83% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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).

## Install

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

ThinkerWave runs locally as a PyPI package, launched with uvx thinkerwave-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 thinkerwave-ai-thinkerwave -- uvx thinkerwave-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "thinkerwave-ai-thinkerwave": {
      "command": "uvx",
      "args": [
        "thinkerwave-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "thinkerwave-ai-thinkerwave": {
      "command": "uvx",
      "args": [
        "thinkerwave-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add thinkerwave-ai-thinkerwave -- uvx thinkerwave-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add thinkerwave-ai-thinkerwave --command uvx --arg thinkerwave-mcp
```

### Hermes

```yaml
mcp_servers:
  thinkerwave-ai-thinkerwave:
    command: "uvx"
    args: ["thinkerwave-mcp"]
```

### Netclaw

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

### Vellum

```bash
assistant mcp add thinkerwave-ai-thinkerwave -t stdio -c uvx -a thinkerwave-mcp
```

### Other

```json
{
  "mcpServers": {
    "thinkerwave-ai-thinkerwave": {
      "command": "uvx",
      "args": [
        "thinkerwave-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.

### 2026-11-04 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 83, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-02 (score 68, −14)

- [security regression] Malware scan: pass → unverified

### 2026-11-01 (score 82, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-31 (score 67, −14)

- [security regression] Malware scan: pass → unverified

### 2026-10-29 (score 81, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-10-27 (score 65, +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.

### 2026-10-25 (score 64, −15)

- [security regression] Malware scan: pass → unverified

## MCP tools (6)

### `start_run` (~102 tokens)

Start a ThinkerWave run on a hard, open-ended problem. `given`: facts to keep exactly as written.
\`standards`: what a good answer must do. `pitfalls`: mistakes to avoid. Returns the run id; runs take
several minutes — check back with run_status, then get_answer.

Input parameters:

- `given`
- `max_rounds`
- `pitfalls`
- `problem` (string, required)
- `standards`

Output parameters:

- `result` (string)

### `run_status` (~34 tokens)

Status of a run: round, best score so far, and why it stopped once finished.

Input parameters:

- `id` (string, required)

Output parameters:

- `result` (string)

### `get_answer` (~40 tokens)

The best answer so far (or the final one), its confidence, and each finding tagged
verified / assumption / guess.

Input parameters:

- `id` (string, required)

Output parameters:

- `result` (string)

### `list_files` (~26 tokens)

Files the run produced (charts, tables, notes).

Input parameters:

- `id` (string, required)

Output parameters:

- `result` (string)

### `read_file` (~48 tokens)

Read one produced file: text files as text (up to 200 KB), images as images (up to 1 MB).

Input parameters:

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

### `stop_run` (~27 tokens)

Stop a run. The best answer so far is kept.

Input parameters:

- `id` (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/thinkerwave-ai-thinkerwave/thinkerwave-mcp#diagnostics

## Score history

- 2026-11-04: 84
- 2026-11-03: 83
- 2026-11-02: 68
- 2026-11-01: 82
- 2026-10-31: 67
- 2026-10-30: 81
- 2026-10-29: 81
- 2026-10-28: 65
- 2026-10-27: 65
- 2026-10-26: 64
- 2026-10-25: 64
- 2026-10-24: 79
- 2026-10-23: 78
- 2026-10-22: 78
- 2026-10-21: 77
- 2026-10-20: 62
- 2026-10-19: 61

## Common questions

### What is the ThinkerWave MCP server?

ThinkerWave is an MCP server listed in the public MCP registry as io.github.thinkerwave-ai/thinkerwave. Autonomous research agent for hard problems that labels every claim verified, assumption or guess. This page covers its PyPI package (thinkerwave-mcp).

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

ThinkerWave scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. 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 ThinkerWave MCP server expose?

ThinkerWave exposes 6 tools: start_run, run_status, get_answer, list_files, read_file, stop_run. Their descriptions and schemas cost roughly 277 tokens of context every time the server is loaded.

### Is the ThinkerWave MCP server still maintained?

ThinkerWave 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 ThinkerWave MCP server under?

ThinkerWave declares the Apache-2.0 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/thinkerwave-mcp/
- Socket report: https://socket.dev/pypi/package/thinkerwave-mcp
- Repository: https://github.com/thinkerwave-ai/thinkerwave
- Website: https://thinkerwave.ai/
- Changelog RSS feed: https://verifymcp.io/servers/thinkerwave-ai-thinkerwave/thinkerwave-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/thinkerwave-ai-thinkerwave/thinkerwave-mcp.json
- HTML version of this page: https://verifymcp.io/servers/thinkerwave-ai-thinkerwave/thinkerwave-mcp