NoBrainer Tech Flow

NoBrainer Tech Flow MCP server

A free, public, stateless remote MCP server for nobrainer-tech-flow. It gives an AI agent one task contract, one evidence check and one done gate, the same in every MCP client, plus guidance quoted from the pinned Flow release and a model advisor based on the NoBrainer AI benchmark.

• Endpoint: https://mcp.nobrainer.tech/mcp, Streamable HTTP, no sign-in.
• Stores nothing, runs no AI model, makes no outbound requests from tools.
• Protocol: MCP 2026-07-28 (stateless, server/discover) and 2025-era clients (2025-11-25, 2025-06-18, ...) through a stateless JSON-only fallback on the same endpoint.

Tools

All six tools are read-only (readOnlyHint: true, openWorldHint: false). Results are one compact JSON text block. Responses never echo your free text: only IDs, enums, digests and canonical Flow text.

The server checks consistency, not truth: it cannot see your machine, and evidence is reported by the agent. Every handoff says so. A recognised failure in the last 4,000 normalized characters of a test log rejects an exit-zero result, even if a later summary passes. Submit a clean rerun separately.

Install

Server name: nobrainer-tech-flow. To try a local build instead, replace the URL with http://127.0.0.1:8787/mcp (see "Run locally").

Claude Code:

claude mcp add --transport http nobrainer-tech-flow https://mcp.nobrainer.tech/mcp# for all projects of this user:claude mcp add --transport http --scope user nobrainer-tech-flow https://mcp.nobrainer.tech/mcp

Project file .mcp.json:

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

Claude.ai and Claude Desktop (not verified): Customize > Connectors > Add > Add custom connector, name NoBrainer Tech Flow, URL https://mcp.nobrainer.tech/mcp, No sign-in. On Team and Enterprise an Owner adds it under Organization settings > Connectors first.

Codex CLI and IDE, ~/.codex/config.toml (or codex mcp add nobrainer-tech-flow --url https://mcp.nobrainer.tech/mcp):

[mcp_servers.nobrainer-tech-flow]url = "https://mcp.nobrainer.tech/mcp"

ChatGPT (not verified): open ChatGPT Plugins (chatgpt.com/plugins), select + > Add custom MCP server, name it NoBrainer Tech Flow, enter the URL under Connection, choose no authentication and select Create as a plugin. Workspace policies decide who can add custom MCP servers.

Cursor, .cursor/mcp.json or ~/.cursor/mcp.json (not verified):

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

VS Code / GitHub Copilot, .vscode/mcp.json (not verified):

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

Gemini CLI (not verified):

gemini mcp add --transport http nobrainer-tech-flow https://mcp.nobrainer.tech/mcp

or settings.json: {"mcpServers": {"nobrainer-tech-flow": {"httpUrl": "https://mcp.nobrainer.tech/mcp"}}}

Cline, cline_mcp_settings.json (not verified; set type, because a missing type means legacy SSE):

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

OpenCode (verified 2026-10-23 against the public endpoint, OpenCode 2.0.32: opencode mcp list shows it connected):

opencode mcp add nobrainer-tech-flow --url https://mcp.nobrainer.tech/mcp --global

Windsurf, ~/.codeium/windsurf/mcp_config.json, then Refresh in Manage MCPs (not verified):

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

Zed, Settings > AI > MCP Servers > Add Remote Server, or settings.json (not verified):

{"context_servers": {"nobrainer-tech-flow": {"url": "https://mcp.nobrainer.tech/mcp"}}}

Using it with local Flow skills

The server leads the gates; guidance already in context leads the guidance. If Flow skills are installed locally, keep using them for stage guidance and call get_flow_step only for cards you have not loaded. Pass your local Flow version as local_flow; when it is older than the server's, the response says that gate rules follow the server's version.

In repository work, save the contract token in the Flow goal file as FLOW_CONTRACT: nbf1... so another session or client can continue. To resume, call get_flow_step with that token and event: "resume". Merge the returned goal_block into the goal file by item ID: update each DoD row's status, CHECKPOINT, NEXT_SAFE_ACTION and FLOW_CONTRACT (the renewed token), and keep your own OUTCOME, NON_GOALS, DoD wording, evidence pointers and other fields. Without a goal file yet, start one from the block and fill in those placeholders. Then continue from NEXT_SAFE_ACTION. Each check_flow_evidence call or resume renews a token for 30 days, up to 90 days after start_flow_task.

Run locally

Node.js 22.18 or newer (TypeScript runs directly through Node's type stripping).

cd mcpnpm cinpm run serve            # http://127.0.0.1:8787/mcp, loopback only, ephemeral signing keynpm test                 # type check, content pin, unit, protocol, security and budget testsnpm run conformance      # official MCP conformance suite (2025-11-25) with test/conformance-baseline.ymlnpm run smoke -- http://127.0.0.1:8787/mcpnpm run transcripts      # rewrites docs/review/test-cases.mdnpm run transcripts -- --in-memory  # SDK tool calls without an HTTP listener; transport is recordednpm run plugin           # dist/nobrainer-tech-flow-<version>.zip for the OpenAI portal

Without FLOW_TOKEN_KEYS, the local server signs with a random key per start, so tokens do not survive a restart. On Vercel the key is required.

How it is built

api/mcp.js          Vercel Function; logic compiled from src/ into dist/ by `npm run build`src/rpcguard.ts     fixed-text answers for unknown tool/prompt/resource names, protocol error rewritingsrc/http.ts         POST only (plus CORS preflight for allow-listed origins), 32 KiB body cap, Host and Origin checks, JSON depth limit, one                    content-free log line; 2026-07-28 traffic -> SDK handler (JSON responses),                    2025-era traffic -> fresh stateless transport with JSON responsessrc/server.ts       six tools, prompt `flow`, resource template `flow://card/{id}`, instructionssrc/token.ts        176-byte max binary token, HMAC-SHA-256 (128-bit tag), key ring, expirysrc/evidence/       runner parsers, verdicts, staleness, failure budget, secret screeningsrc/rules/          levels, quick/full path, lint, module routing, owner gatessrc/advisor/        model advisor over data/benchmark/snapshot.jsoncontent/            SOURCE.json pin (tag, commit, file hashes) and cards.yamlsrc/generated/      cards.json built by scripts/build-content.ts from the git tagplugin/             OpenAI submission manifests (plugin.json, mcp.json)

Runtime dependencies: @modelcontextprotocol/server 2.3.1, zod 4.6.7, @vercel/firewall 1.2.6. The spec proposed mcp-handler; it is a thin wrapper over the SDK's own createMcpHandler, so the server uses the SDK directly (one dependency fewer, same dual-era behaviour).

Updating Flow guidance

The module list comes from the release: scripts/build-content.ts enumerates skills/*/SKILL.md at the pinned tag. A released module without a cards.yaml entry gets a description-only card and a warning; a cards.yaml module entry that the release no longer has fails the build (this is how a rename such as nobrainer-codex-context -> nobrainer-context surfaces). To move to a new release: update content/SOURCE.json (tag, commit, hashes), fix cards.yaml, run npm run build:content and npm test, then deploy.

Updating the benchmark snapshot

npm run refresh:benchmark -- --source <website>/public_html/ai/benchmark regenerates data/benchmark/snapshot.json and SOURCE.json deterministically. The website rule applies: a snapshot expires 14 days after its fetch time, so refresh and redeploy at least every 14 days or the advisor answers expired: true with an empty shortlist. See data/benchmark/NOTICE.md for provenance and third-party licences.

Documents

• Deployment: build, checks, environment variables, rate limits, spend guard.
• Security: threat model and controls.
• Privacy policy and terms, published at https://nobrainer.tech/flow/privacy/ and https://nobrainer.tech/flow/terms/.
• Review test cases and demo recording script.

Source code: MIT, see the repository LICENSE.