# NoBrainer Tech Flow

> NoBrainer Tech Flow is an open-source MCP server for developer tools. Task contract, evidence check and done gate for coding agents over remote MCP. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** API
- **Website:** https://nobrainer.tech/flow/
- **Repository:** https://github.com/nobrainer-tech/nobrainer-tech-flow/tree/HEAD/mcp
- **MCP Registry name:** io.github.nobrainer-tech/nobrainer-tech-flow
- **Categories:** developer tools
- **Listing updated:** 2026-11-14

## About

The pitch is that an agent should not be able to declare victory without proof. The server is public and stateless, runs no AI model, stores nothing and makes no outbound requests from its tools. All six tools are read-only, and responses carry IDs, enums, digests and canonical text rather than echoing what you wrote.

A task starts with start_flow_task, which checks the outcome and definition of done, lints vague items and returns item IDs such as AC01 with an HMAC-signed contract token to keep in a goal file. check_flow_evidence then reviews evidence records such as exit codes and test-runner summaries from pytest, Vitest, Jest, Go, cargo and others, and marks earlier results stale when a registered file changes. check_flow_done answers DONE, DONE_WITH_GAPS or NOT_DONE with the missing items.

There is also recommend_flow_model, which suggests a top-3 model shortlist from a dated benchmark snapshot and refuses once that snapshot is 14 days old. The README is candid that it checks consistency, not truth, since the evidence is reported by the agent.

## Features

- **Task contract:** start_flow_task checks the definition of done and issues a signed contract token.
- **Flow rule lookup:** get_flow_step quotes up to six rules per stage verbatim from the pinned release.
- **Evidence checking:** Reviews test summaries, exit codes and file hashes.
- **Done gate:** Returns DONE, DONE_WITH_GAPS or NOT_DONE with the exact missing items.
- **Handoff draft:** Builds a final report skeleton from the done receipt.
- **Model advisor:** Suggests models for a task type from a dated benchmark snapshot.

## Good for

- Stop a coding agent marking a task done without passing tests
- Turn a vague request into checkable acceptance items
- Resume a task with a goal block that records each item's status
- Pick a model for terminal coding or frontend work

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http nobrainer-tech-flow https://mcp.nobrainer.tech/mcp
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://mcp.nobrainer.tech/mcp
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "nobrainer-tech-flow": {
      "url": "https://mcp.nobrainer.tech/mcp"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "nobrainer-tech-flow": {
      "type": "http",
      "url": "https://mcp.nobrainer.tech/mcp"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "nobrainer-tech-flow": {
      "serverUrl": "https://mcp.nobrainer.tech/mcp"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "nobrainer-tech-flow": {
      "type": "http",
      "url": "https://mcp.nobrainer.tech/mcp"
    }
  }
}
```

## Tools

- `start_flow_task`: Check the outcome and definition of done and return a signed contract token
- `get_flow_step`: Quote up to six rules for a stage, event, module or topic
- `check_flow_evidence`: Check one to four evidence records such as exit codes and test summaries
- `check_flow_done`: Return DONE, DONE_WITH_GAPS or NOT_DONE
- `draft_flow_handoff`: Build a final-report skeleton from the done receipt
- `recommend_flow_model`: Top-3 model shortlist for a task type from a dated benchmark

## FAQ

### Do I need to sign in?

No. The endpoint at mcp.nobrainer.tech/mcp is free, public and needs no sign-in.

### Does it store my code or prompts?

The README says it stores nothing, runs no AI model and never echoes your free text.

### Can it prove the work is correct?

No. It checks consistency of reported evidence; it cannot see your machine.

### Which license?

The site says Flow is free, open source and MIT.

### Is NoBrainer Tech Flow free?

Yes. NoBrainer Tech Flow is open source, so you can use and self-host it for free.

### How do I add NoBrainer Tech Flow to Claude Code?

Run this command in your terminal: claude mcp add --transport http nobrainer-tech-flow https://mcp.nobrainer.tech/mcp

### What are the best alternatives to NoBrainer Tech Flow?

The closest alternatives to NoBrainer Tech Flow are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/nobrainer-tech-flow
