Skip to main content
Glama

Protocol-X Tool MCP

A security-first MCP server that wraps the most-used Python packages as schema-validated, sandboxed tools — 34 launch-core tools across Pillow, requests, pypdf, pandas, openpyxl, and python-docx — plus an autonomous ReAct converter agent (governed by an NVIDIA Nemotron AI-judge on Nebius Token Factory) that grows the catalog by requirement, with runtime self-repair, a control console at localhost:7894, and a hardened Docker profile.

Quickstart

uv sync
uv run protocol-x-tool-mcp serve --transport stdio
# or HTTP + console:
uv run protocol-x-tool-mcp serve --transport http   # http://127.0.0.1:7894

See docs/quickstart.md for the full install → first-call flow (< 5 minutes).

Related MCP server: Sandbox MCP Server

Layout

  • server/ — MCP app (FastMCP), transports, auth/ACL, rate limit, registry, health, config

  • core/ — sandbox runner + worker pool, workspace confinement, serialization, secrets, sizing, SQLite store, audit, logging

  • agents/ — Token Factory client, Nemotron AI-judge, ReAct converter, runtime self-repair

  • adapters/ — auto-discovered tool adapters (built-ins + converter-generated)

  • console/ — React + TypeScript control console (served by the server from console/dist/)

  • templates/ — Jinja codegen/rendering templates · migrations/ — SQLite schema · policies/ — sandbox presets

  • scripts/ — operator scripts (install, doctor, per-use-case tests) · docs/ — full documentation

How we used NVIDIA Nemotron + Nebius Token Factory / AI Cloud

All agent inference — the AI-judge (F-019), the ReAct package converter (F-029), and the runtime self-repair agent (F-030) — calls NVIDIA Nemotron open models via Nebius Token Factory (Nemotron 3 Ultra for judging and codegen escalation; Nano/Super for fast converter/repair loops). The server, sandbox, and console deploy on Nebius AI Cloud VMs via the hardened Docker profile. Endpoint and model names are configurable via PROTOX_TF_* env vars; without a key the server runs in degraded mode with the 34 core tools fully live and agent features explicitly disabled.

Verify

uv run pytest -q          # full suite (unit, integration, security, adversarial, e2e, benchmarks)
uv run ruff check         # lint
uv run mypy server core agents adapters  # types
uv run lint-imports       # layering contract: server -> agents -> core -> adapters
scripts/test.sh           # everything above + per-use-case scripts -> docs/test-results.md
scripts/check-no-telemetry.sh            # privacy gate: zero phone-home references

Per-use-case suites: scripts/test-uc-01.sh … test-uc-07.sh (guides in docs/use-cases/; uc-06 green-skips until the v1.1 polyglot backends land).

Documentation

  • docs/quickstart.md — install → first call in minutes

  • docs/connecting-mcp-clients.md — connect Claude Desktop/Code, Kimi Code, Cursor, and custom agents (stdio + HTTP)

  • docs/cli-reference.md · docs/environment-variables.md — complete operator references

  • docs/features.md · docs/architecture.md · docs/security.md — capabilities, module tree + agent loops, threat model (INV-1…8)

  • docs/use-cases/uc-01…07.md — persona walkthroughs · docs/contributing.md — dev setup and PR gates

License

Apache-2.0 — see LICENSE.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to create isolated Docker runtimes, execute commands, manage workspace files, drive a headed browser, and retrieve artifacts through eight semantic MCP tools, with progressive capability discovery and explicit sandbox lifecycle.
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables MCP hosts to run auditable multi-agent work through a SQLite task registry, DAG orchestration, three collaboration modes (pipeline, iterative refinement, and proposal voting), human-in-the-loop approvals, an enforced sandbox, compliance scanning, and long-term memory. Exposes these capabilities as 36 tools so every consequential step stays gated behind a human checkpoint.
      AGPL 3.0
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to route Office and PDF tasks through a single MCP interface, including Word/Excel/PowerPoint reads and edits, zero-loss Excel XML edits, PPTX/DOCX generation, Markdown-to-Word conversion, and multi-strategy PDF parsing, while enforcing workspace and write-safety gates.
      MIT