Skip to main content

Trace2MCP

Teach once. Run forever.

Trace2MCP compiles a successful AI-agent tool-call trace into a deterministic, inspectable, MCP-ready workflow.

An agent can discover a useful procedure once. Trace2MCP then validates the trace, infers data dependencies, deduplicates safe reads, builds a directed acyclic graph (DAG), and identifies work that can run concurrently.

Install

pip install trace2mcp

To run generated MCP servers, install the optional MCP dependency:

pip install "trace2mcp[mcp]"

Python 3.10 or newer is required.

Try it

trace2mcp inspect trace.json
trace2mcp compile trace.json --out build/my-workflow
trace2mcp benchmark trace.json --repetitions 3

Or use the Python API:

from trace2mcp import compile_trace, load_trace

trace = load_trace("trace.json")
workflow = compile_trace(trace, allow_side_effects=False)

print(workflow.to_dict())

The compile command produces a portable workflow.json, inert handler stubs, and a minimal MCP server skeleton. You provide the real tool implementations; observed trace outputs are never converted into executable code.

Why compile traces?

  • Lower orchestration overhead: reuse a discovered procedure instead of planning the same tool path on every run.
  • Dependency-aware execution: independent read-only calls can run in parallel.
  • Fail-closed safety: writes and unknown operations are rejected unless explicitly allowed.
  • Auditability: tool calls, references, dependencies, and scheduling remain visible as portable JSON.
  • Provider-neutral design: the core compiler does not require a model or an API key.

Live demo

Use the free, browser-only Trace2MCP interactive demo or visit the Hugging Face Space.

The included demo uses synthetic outputs and recorded durations to explain the scheduler. Its speedup is educational, not a production performance claim.

Safety

Trace2MCP is a research prototype. Review generated workflows and implement authorization, validation, timeouts, and least-privilege access around real tools before production use.

Licensed under the MIT License.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

trace2mcp-0.1.0.tar.gz (29.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

trace2mcp-0.1.0-py3-none-any.whl (24.9 kB view details)

Uploaded Python 3

File details

Details for the file trace2mcp-0.1.0.tar.gz.

File metadata

  • Download URL: trace2mcp-0.1.0.tar.gz
  • Upload date:
  • Size: 29.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.10

File hashes

Hashes for trace2mcp-0.1.0.tar.gz
Algorithm Hash digest
SHA256 e60be38c05b837b9685bcb4da6491098dc48d6de34cda0637a7f490ee4ac5542
MD5 5d1703fc7904f342c3731937f9c7a15b
BLAKE2b-256 5977cfbfe5c4f411797502ffdb0977b852d919fd6ecca1147e71bc8c15f233a9

See more details on using hashes here.

File details

Details for the file trace2mcp-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: trace2mcp-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 24.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.10

File hashes

Hashes for trace2mcp-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 9305a9221314dc498d4ee92c23c45fb224ee0cb5ef1652b434dc51b806778d59
MD5 14f8432cb36f16aabbe668aa760d6d65
BLAKE2b-256 01302c122fa5b8d79c85cd786baf0cc2aac23090a8b310b926d85f239a8007b1

See more details on using hashes here.

Release history Release notifications | RSS feed

0.2.1

2 files

0.2.0

2 files

This release

0.1.0 This release

2 files

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page