ops-mcp-server
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
ops-mcp-server
A Model Context Protocol (MCP) server that gives an AI agent safe, auditable access to operations data and actions: KPIs, team capacity, runbooks, and approval requests.
The protocol layer is implemented from scratch (JSON-RPC 2.0 over stdio, standard library only) so every design decision is visible. The interesting part is not the plumbing but the tool-safety design: what an agent is allowed to read, what it is only allowed to request, and how bad input is handled.
Tools
Tool | Kind | What it does |
| read-only | Value, target and red/amber/green status for one or all KPIs |
| read-only | Assigned vs available hours per team, flags HIGH / OVER |
| read-only | Ranked search over operational runbooks |
| write (limited) | Creates a pending approval request. It never performs the business action |
Each tool advertises a JSON Schema and MCP annotations (readOnlyHint, destructiveHint, ...) so a client can decide what to auto-approve.
Related MCP server: MCP Engineering Agent
Run it
pip install -e .
opsmcp --data data --db approvals.dbSmoke test by hand (one JSON message per line):
printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18"}}' \
'{"jsonrpc":"2.0","method":"notifications/initialized"}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"capacity_check","arguments":{}}}' \
| opsmcp --data data --db :memory:Connect it to an MCP client such as Claude Desktop by adding this to its config:
{
"mcpServers": {
"ops": { "command": "opsmcp", "args": ["--data", "/path/to/data", "--db", "/path/to/approvals.db"] }
}
}Safety design
Read tools cannot change anything. They only read files from one data directory.
The write tool only requests.
request_approvalrecords a pending row. Approving and executing happen elsewhere, by a human (this is the same autonomy idea as inagentflow-hitl).Arguments are untrusted. Strict validation: required fields, types (a boolean is not an integer), enums, bounds, length limits, and unexpected fields are rejected.
Tool errors are returned to the model, not thrown. Bad input gives
isError: truewith a helpful message ("no KPI named x; available: ..."), so the model can recover. Protocol errors (unknown tool, malformed message) use JSON-RPC error codes.No internals leak. Unexpected exceptions return only the exception type.
Path confinement. File access is resolved and checked to stay inside the data directory.
stdout is the protocol. Logging goes to stderr only; a stray print would corrupt the stream.
The server survives garbage. An invalid JSON line returns a parse error and the loop continues.
Tests
23 tests, including a subprocess test that speaks to the server over real stdio.
PYTHONPATH=src python -m unittest discover -s tests -vSee ARCHITECTURE.md for the protocol notes and limitations.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Runtime permission, approval, and audit layer for AI agent tool execution.
Read-only finance and operations controls for AI agents with evidence and safe next actions.
Security gateway for AI agents: policy, approval, and audited execution, no secrets shared.
Related MCP Servers
- FlicenseNot gradedqualityCmaintenanceEnables controlled AI-agent access to enterprise-shaped tools with a deny-by-default gated write path, human approval, dry-run execution, and append-only audit logging.1-
- FlicenseNot gradedqualityBmaintenanceEnables a security-first engineering agent with an MCP-style JSON-RPC tool boundary, role-based authorization, and UTC audit events for every decision.-
- AlicenseAqualityCmaintenanceEnables AI agents to browse customers, bookings, and availability while any booking creation or cancellation stays gated behind a human-approved, single-use token cryptographically bound to the exact arguments. Runs over stdio or Streamable HTTP and enforces the read/write separation in host code with a full audit trail.7MIT
- AlicenseNot gradedqualityBmaintenanceEnables read- or write-scoped access to synthetic enterprise orders, inventory, support tickets, and metrics via schema-validated JSON-RPC tools over stdio and HTTP, with permission allow-lists and audit logging. It also exposes enterprise resources and prompt templates for grounded, cited, multi-step assistant workflows.MIT