mcpField
T
ThinkerWave

ThinkerWave

Local
thinkerwave.aiAI & Agents0Updated 1w ago
RepositoryVisit website

About ThinkerWave

ThinkerWave is a cloud-based autonomous research agent for open-ended business and scientific questions. It iteratively researches and checks its calculations, returning confidence and evidence labels for each claim.

Key features

  1. 01Iterative research and self-checking
  2. 02Numerical analysis
  3. 03Claim labels: verified, assumption, guess
  4. 04Evidence, charts and tables
  5. 05Python SDK and tw CLI

Use cases

  1. 01Compare pricing choices against churn data
  2. 02Run credit risk stress tests
  3. 03Assess market entry or due diligence
  4. 04Select drug development programs

MCP support

The repository includes an MCP server that lets clients such as Claude Code or Cursor submit questions to ThinkerWave and receive answers with evidence.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "thinkerwave-ai-thinkerwave": {
      "command": "uvx",
      "args": [
        "thinkerwave-mcp"
      ],
      "env": {
        "THINKERWAVE_API_KEY": "<THINKERWAVE_API_KEY>"
      }
    }
  }
}
Run commanduvx thinkerwave-mcp
Environment variables to set
THINKERWAVE_API_KEYSecretYour ThinkerWave API key (thinkerwave.ai/app → Settings → API keys)

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypithinkerwave-mcp0.1.2

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

ThinkerWave

PyPI Python License MCP server CI

An autonomous research agent for problems without a single right answer — credit risk stress tests, pricing and churn, market entry, due diligence, drug program selection.

You give it the problem and the facts you're sure of. It researches, runs the numbers, checks its own work and tries again, round after round, keeping the best answer. You get the answer, how confident it is, and the evidence behind each claim — verified, assumption or guess — plus any charts and tables it produced.

A real two-round ThinkerWave run in the terminal

pip install thinkerwave
export THINKERWAVE_API_KEY=tw_live_…      # create one at thinkerwave.ai/app → Settings → API keys
tw run "Should we raise prices 15%, 8%, or hold? 1,200 customers at \$85/month, 3.1% monthly churn." \
  --given "last 8% increase spiked churn to 4.6% for three months" --rounds 6 --watch

From Claude Code or Cursor: pip install "thinkerwave[mcp]", then claude mcp add thinkerwave -- thinkerwave-mcp — your coding assistant can now hand ThinkerWave a hard question and read back the evidence.

From Python: see examples/.

What's in this repo: the Python SDK, the tw command line, an MCP server, the API reference and the answer/evidence format. ThinkerWave itself runs in ThinkerWave's cloud; this repository is the way in, not the engine.

Free runs are included with every account. Limits: docs/limits.md. Found a problem it got wrong? Open an issue with the run id.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.