Best for
- Developers already using Binex who want to inspect runs through a coding agent
- Teams needing a local-first, debuggable agent workflow toolchain
B
Binex MCP Server
Community
Open-source visual orchestrator for AI agent workflows, 100% local
GitHub source repository ↗
45FMRS · D
Binex is a local-first, MIT-licensed runtime for AI agent workflows whose MCP server exposes runs, evals, and artifacts to coding agents. It is best suited to developers who want to debug and compare workflows without migrating their existing frameworks, but it requires a local Binex install on Python 3.11+ and offers no hosted cloud option.
Binex is an open-source, fully local runtime for AI agent workflows, offering DAG pipelines, artifact lineage, and replayable runs. Through binex mcp serve, it exposes runs, evals, and artifacts as MCP tools for Claude Code, Cursor, or any MCP-compatible agent. The project is built with Python, React, FastAPI, and TypeScript, is MIT licensed, and includes no telemetry.
Tools
binex_debug
Inspect per-node inputs and outputs of a run as a post-mortem.
binex_eval_run
Run a YAML eval suite against blessed baselines for regression testing.
binex_diff
Compare two runs side by side with filtering for changes, failures, and cost deltas.
Setup
- Install:
pip install binex(requires Python 3.11+). - Register Binex as an MCP server:
claude mcp add binex -- binex mcp serve. - Launch from Claude Code, Cursor, or another MCP-compatible client to use the binex_debug, binex_eval_run, and binex_diff tools.
claude_desktop_config.json
{"mcpServers":{"binex":{"command":"binex","args":["mcp","serve"]}}}
Fit and risk
Not for
- Users wanting a hosted cloud tracing service instead of a local runtime
- Environments without Python 3.11+ and Binex installed
Required permissions
- Read and write the local Binex store (default `.binex` directory with a SQLite database and JSON artifact files)
- Read locally configured LLM provider API keys (needed to run workflows)
- Communicate with the MCP client process over stdio
Risks and side effects
- Exposed runs, evals, and artifacts are written to the local `.binex` directory and may contain sensitive prompts or outputs
- If cloud LLM providers are configured, prompts and data are sent to those providers
- Any local process able to invoke the MCP server can read run data
Troubleshooting
- Verify the `binex` command is on PATH and Python is 3.11 or newer
- Check the MCP client config uses the command and args `binex mcp serve`
- Confirm the `.binex` store directory is writable, or check the `BINEX_STORE_PATH` environment variable
- Restart the MCP client and check its logs if tools do not appear
Use cases
Inspect and debug Binex workflow runs from Claude Code or Cursor
Run eval suites against baselines for agent pipelines
Compare two runs to spot node-level divergence and cost changes
Supported clients
Claude CodeFull support
CursorPartial support