Skip to main content
Glama

MCP tools and a reliable agent

CI

Status: planned. Work starts Feb 2027. This README is the plan. Each number appears only after it has been measured.

A TypeScript MCP server for orders and refunds, and an agent measured by pass^k, cost per task and how safely it fails.

Demo (2 min): coming · Live: coming · Write-up: coming

Problem

Who has it, what "good" looks like for them, and why it is hard. Three lines.

Related MCP server: CodeForge MCP

Results

Version

Metric A

Metric B

p95 latency

Cost / 1k requests

Baseline

–

–

–

–

Eval set: N items, source, labelled by how. Judge agreement with human labels: x% (n=n). Intervals: 95% bootstrap.

Architecture

Diagram goes here.

  • Ingestion / input: ...

  • Core logic: ...

  • Evals: ...

  • Observability: ...

What I tried that didn't work

  • Experiment: what happened, and why I think it happened.

Security and privacy

Threats considered, mitigations, what is out of scope.

Run it

git clone https://github.com/AbirHasanPiash/orders-mcp-agent.git
cd orders-mcp-agent
cp .env.example .env   # then add your own keys
make setup             # install dependencies and git hooks
make check             # lint, format check, tests
make eval              # eval suite (calls models, uses API quota)

Tests and CI

Unit tests, an eval subset with pass thresholds, and lint checks on every push and pull request.

With two more weeks I would

  • ...


License: MIT. Part of a year-long build plan by AbirHasanPiash.

Related MCP Connectors

Related MCP Servers

  • F
    license
    A
    quality
    D
    maintenance
    A TypeScript MCP server for launching, tracking, and managing external coding-agent runs across local and remote backends like Codex and Claude Code. It allows top-level agents to orchestrate subagents through tools for spawning tasks, polling events, and handling interactive sessions.
    7
    2
    -
  • A
    license
    Not graded
    quality
    D
    maintenance
    A self-hosted MCP server that provides a single execute_code tool, enabling agents to write TypeScript to call multiple REST APIs via fetch() with transparent credential injection, reducing token usage by keeping intermediate results in the sandbox.
    11
    BSD 3-Clause
  • A
    license
    D
    quality
    D
    maintenance
    A TypeScript MCP server demo supporting local Stdio and remote Streamable HTTP, demonstrating tool invocation for AI agents.
    2
    1
    MIT
  • -
    license
    Not graded
    quality
    C
    maintenance
    Intelligent server management MCP server that enables agents to write TypeScript code to organize and manage multiple MCP servers with self-improving capabilities.
    2
    -