Skip to main content
Glama
entagent
by iarsingh

Enterprise AI Agent Platform

Overview

An agent tool gateway that exposes only allowlisted MCP tools. GET /tools lists what an agent may use, and POST /call runs a tool only if it is on the enterprise allowlist; requests to apply changes are refused. A versioned /v1 ops API adds workspaces, tenant isolation, job approval and audit records for agent jobs.

  • Built with: Python, pytest, Docker, GitHub Actions

  • Scope: Local laptop proof with tests; it does not call a hosted model and refuses production apply.

Related MCP server: dsh-mcp-bridge

Project guide

Project architecture · Interview questions and answers

Use the architecture document for the component diagram, implementation boundaries, and verification entry points. The interview guide includes source-backed answers and project walkthroughs.

Implementation map

Component

Responsibility

src/entagent/main.py

HTTP handlers: GET /healthz, GET /tools, POST /call

src/entagent/ops.py

HTTP handlers: GET /readyz, POST /workspaces, GET /workspaces, POST /workspaces/{workspace_id}/jobs, GET /jobs/{job_id}

src/entagent/mcp.py

Functions: list_tools, call

requirements.txt

Implementation or supporting configuration

src/entagent/__init__.py

Implementation or supporting configuration

Dockerfile

Container build/service configuration

Makefile

Implementation or supporting configuration

docker-compose.yml

Container build/service configuration

tests/test_mcp.py

Executable checks and regression examples

tests/test_ops.py

Executable checks and regression examples

.github/workflows/ci.yml

GitHub Actions job definitions

README.md

Project explanations or operating notes

docs/ARCHITECTURE.md

Project explanations or operating notes

Local setup and verification

From the repository root (the commands follow the checked-in manifests):

python3 -m venv .venv
source .venv/bin/activate
python -m pip install -r requirements.txt
python -m pytest -q

To serve the FastAPI application locally, install the server separately if it is not already available:

python -m pip install uvicorn
PYTHONPATH=src python -m uvicorn entagent.main:app --reload

Level: 17 — Advanced Enterprise AI

Skills: Python, enterprise MCP allowlist

Allowlisted tools only. Apply refused.

pip install -r requirements.txt
pytest -q

This is a local laptop proof. It does not call a hosted model and it does not apply production changes.

Ops plane

Workspaces, tenant isolation, job approval, and audit live under /v1. Production apply is refused. See docs/ARCHITECTURE.md.

Documentation checks

Project architecture, interview guides, and local source links are checked automatically on pushes and pull requests. Run the same check locally:

python3 .github/scripts/validate_project_docs.py

See service improvements and local run instructions.

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
      D
      maintenance
      Enables per-profile tool filtering and enforcement for one or more upstream MCP servers, exposing only allowed tools and rejecting blocked calls, with Streamable HTTP serving and observability.
      970,284 npm
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Exposes DeepSeek Harness tools to any MCP-compatible client over streamable HTTP, allowing allowlisted operations such as file read, glob, grep, and web search while preserving the harness's sandbox and approval pipeline.
      681 npm
      2
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables building and testing MCP-style tool servers by exposing list_tools and call_tool over stdio or HTTP with local stub tools such as echo, get_time, and fake_crm_lookup.
      MIT