engineering-context-mcpSAFE
Open-source MCP platform connecting AI applications with engineering tools, documentation, and workflows.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An open-source Python project for building MCP-powered integrations between AI applications and engineering tools, documentation, and workflows.
[](https://github.com/shared-wks/engineering-context-mcp/actions/workflows/ci.yml)
Current version: 0.1.0 Status: MCP foundation implemented; business integrations in development License: MIT
Overview
Engineering Context MCP explores how Model Context Protocol (MCP) can expose engineering data and workflows to compatible AI applications.
The current implementation is a working Python MCP client and server, with an in-memory task-management example.
The long-term goal is to integrate Jira, Confluence, and other engineering platforms into a containerized, secure MCP service.
Technology Stack
Implemented
- Python 3.12+
- Official MCP Python SDK (v1.x)
- FastMCP
- Python venv and pip
- pytest
- Ruff
- GitHub Actions
Planned
- Docker and Docker Compose
- PostgreSQL
- SQLAlchemy and Alembic
- Streamable HTTP transport
- Jira Cloud and Confluence Cloud APIs
- OpenTelemetry and improved observability
Prerequisites
To run version 0.1.0, you need:
- Python 3.12 or newer
- Git
- pip (included with most Python installations)
Optional:
- Node.js and npm for MCP Inspector
- An IDE such as VS Code or PyCharm
Docker, a PostgreSQL server, an LLM, and Atlassian API credentials are not required for this release.
Installation
1. Clone the repository
Using HTTPS:
git clone https://github.com/shared-wks/engineering-context-mcp.git cd engineering-context-mcp
SSH is also supported if you have registered an SSH key:
git clone [email protected]:shared-wks/engineering-context-mcp.git cd engineering-context-mcp
Use either clone method, not both.
2. Create a virtual environment
macOS / Linux
python3 -m venv venv source venv/bi
b0d7af50ee66OBSERVED · 2026-10-11Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add engineering-context-mcp -- uvx engineering-context-mcp
{
"mcpServers": {
"engineering-context-mcp": {
"command": "uvx",
"args": [
"engineering-context-mcp"
]
}
}
}Exposed tools (4)
2 read · 1 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_task | write | Create a new task using its title. |
complete_task | read | Mark an existing task as completed. |
delete_task | destructive | Delete an existing task by its ID. |
list_tasks | read | Return all existing tasks. |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (1 observation(s))
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
delete_task
.gitlab-ci.yml
> Continue **Engineering Context MCP**. Read `docs/PROJECT_HANDOVER.md` first; it is the project continuity source. Use standard Python `venv` and `pip`, not `uv`. The public **GitHub and GitLab** rep
Gates applied: no_behavioural_pass.
b0d7af50ee66full audit observations/trust-audit/mcp-server/shared-wks__engineering-context-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | b0d7af50ee66 | SAFE | B | 89 | first audit |
Questions
What is the engineering-context-mcp MCP server?
Open-source MCP platform connecting AI applications with engineering tools, documentation, and workflows.
What tools does engineering-context-mcp expose?
4 in total: 2 read-only, 1 that write, and 1 that can delete or overwrite (delete_task). Every one is listed on this page with its risk.
Is engineering-context-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does engineering-context-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does engineering-context-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as engineering-context-mcp.
How current is this page?
The grade is for one exact copy of the source (b0d7af50ee66), read on 2026-10-11. The repository is watched and re-audited when it changes.