What can you do with this server?

The OpsMCP server exposes eight typed MCP tools for AI agents to safely operate GitHub, Postgres, deploy status, and a sandboxed local filesystem.\n\n- GitHub operations: list issues/PRs, create issues (dry-run by default), and summarize PR diffs (without patches).\n- Postgres read-only access: run parameterized SELECT queries and EXPLAIN plans, with DDL/DML/multi-statement SQL rejected before connecting.\n- Deploy status: fetch the latest GitHub Actions workflow run for a branch.\n- Sandboxed filesystem: search for literal substrings and read files under allowlisted roots, with symlink/.. escape protection and a size limit.\n- Safety-first design: credentials stay in the server process, tool inputs treated as untrusted, and all outbound HTTP rate-limited.\n- Run locally: via uv run python -m ops_mcp with config via .env, and a companion UI for catalog/setup/playground.

Which integrations are available for this server?

Provides tools for interacting with GitHub's API, enabling listing issues and pull requests, creating issues (with dry-run by default), and summarizing pull request diffs for repository management. Provides a tool to retrieve the latest workflow run status for a branch, allowing monitoring of deployment and CI/CD status from GitHub Actions.

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@OpsMCP check deploy status for main branch" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

OpsMCP

by tanmays0

Overview Schema Source Related Servers Discussions Admin

Python

Local

OpsMCP

MCP (Model Context Protocol) server that exposes eight typed tools so an AI agent can operate GitHub, Postgres, deploy status, and a sandboxed local filesystem. Credentials stay in the server process; tool inputs are treated as untrusted.

Live: https://tanmays0.github.io/ops-mcp/
GitHub: https://github.com/tanmays0/ops-mcp

Artifact	Location
MCP server (stdio)	`uv run python -m ops_mcp`
Eight tools	registered in `src/ops_mcp/server.py`
Companion UI	`site/` → GitHub Pages (catalog, setup, simulated playground)
Seeded demo database	`docker compose up -d` → Postgres `users` / `orders` / `products`
Automated tests	`uv run pytest` (path sandbox, SQL guard, GitHub mocks, Postgres)
CI	GitHub Actions workflow `.github/workflows/ci.yml`
Pages deploy	`.github/workflows/pages.yml`
Container image	`Dockerfile`
Agent wiring example	`.cursor/mcp.json.example`

Architecture

Agent (stdio) → FastMCP server
                  ├── tools/       domain tools
                  ├── security/    path sandbox, SQL allowlist, redaction, rate limit
                  ├── adapters/    GitHub HTTP, Postgres
                  └── config.py    Pydantic Settings (env / .env)

Related MCP server: Sandbox MCP

Tools

Tool	System	Behavior
`github_list_issues`	GitHub API	List issues/PRs by repo, state, labels
`github_create_issue`	GitHub API	Create issue; default `dry_run=true`
`github_pr_diff_summary`	GitHub API	PR file list and diff stats (no patches)
`postgres_query_readonly`	Postgres	Parameterized SELECT only
`postgres_explain`	Postgres	`EXPLAIN (FORMAT TEXT)` only (no `ANALYZE`)
`deploy_status`	GitHub Actions	Latest workflow run for a branch
`fs_search`	Local FS	Literal search under allowlisted roots
`fs_read_file`	Local FS	Read file with sandbox and size limit

Safety

Control	Implementation
Filesystem	Resolve-then-compare allowlist after symlink resolution
SQL	sqlglot AST: single SELECT / WITH…SELECT; DDL/DML/multi-statement rejected before connect
GitHub writes	`dry_run=true` unless explicitly disabled
Secrets	`SecretStr` for token and DSN; log redaction; never returned in tool payloads
Outbound HTTP	Token-bucket rate limit

Stack

Python 3.12 · FastMCP · httpx · psycopg · sqlglot · Pydantic Settings · pytest · Docker

Run

git clone https://github.com/tanmays0/ops-mcp.git
cd ops-mcp
uv sync
docker compose up -d
cp .env.example .env
uv run pytest
uv run python -m ops_mcp

Populate .env from .env.example (OPS_MCP_FS_ROOTS, OPS_MCP_DATABASE_URL, OPS_MCP_GITHUB_TOKEN). MCP client config: copy .cursor/mcp.json.example to .cursor/mcp.json with absolute paths. Secrets load from .env only (.env and .cursor/mcp.json are gitignored).

Configuration

Variable	Purpose
`OPS_MCP_FS_ROOTS`	Colon-separated allowlisted directories
`OPS_MCP_FS_MAX_READ_BYTES`	Max bytes for `fs_read_file`
`OPS_MCP_DATABASE_URL`	Postgres DSN
`OPS_MCP_GITHUB_TOKEN`	GitHub fine-grained or classic PAT
`OPS_MCP_HTTP_RATE_PER_SECOND`	Outbound API rate
`OPS_MCP_LOG_LEVEL`	Log level

Verification flows

Documented end-to-end flows: DEMO.md.

Spec

Project principles: .specify/memory/constitution.md
Requirements: specs/001-ops-mcp-server/spec.md

Available Tools

8 tools

deploy_statusDeploy StatusB

Latest GitHub Actions workflow run for a branch (read-only).

Inputs: repo (required), owner (required), branch. Returns: object

fs_read_fileFs Read FileA

Read a file under allowlisted roots with a hard size limit.

Symlink and .. escapes fail closed. Content is UTF-8 decoded with replacement characters; truncated is true when the file exceeded the cap.

Inputs: path (required), max_bytes. Returns: object

fs_searchFs SearchA

Search allowlisted filesystem roots for a literal substring.

Returns matches only under OPS_MCP_FS_ROOTS. Paths that escape the sandbox (including via .. or symlinks) are rejected.

Inputs: query (required), root, max_results. Returns: object

github_create_issueGithub Create IssueA

Create a GitHub issue. Defaults to dry_run=True (no remote write).

Set dry_run=False only when the user explicitly confirms creation. Never returns credentials.

Inputs: repo (required), owner (required), title (required), body, +2 more. Returns: object

github_list_issuesGithub List IssuesA

List GitHub issues/PRs for a repo by state and labels.

Requires OPS_MCP_GITHUB_TOKEN. Returns number, title, state, labels.

Inputs: repo (required), owner (required), state, labels, +1 more. Returns: object

github_pr_diff_summaryGithub Pr Diff SummaryC

Summarize a PR's changed files and diff stats without full patches.

Inputs: repo (required), owner (required), pull_number (required). Returns: object

postgres_explainPostgres ExplainA

EXPLAIN (FORMAT TEXT) a SELECT without ANALYZE / executing side effects.

Inputs: sql (required), params. Returns: object

postgres_query_readonlyPostgres Query ReadonlyA

Run a parameterized SELECT against Postgres (DDL/DML rejected first).

Requires OPS_MCP_DATABASE_URL. Multi-statement and write SQL fail closed before any connection is opened.

Inputs: sql (required), params, max_rows. Returns: object

Tool Schema Changelog

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

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.6/5.0

Scored 2026-09-15 00:55 across 8 tools

Disambiguation5/5

Each tool targets a distinct resource and action: filesystem search/read, GitHub issues/PR summary, Postgres query/explain, and deployment status. Even the PR-related tools are clearly separated by list vs. diff-summary purpose.

Naming Consistency3/5

Names use consistent resource prefixes (fs_, github_, postgres_, deploy_) and many follow verb_noun, but github_pr_diff_summary and deploy_status are noun phrases without a verb, and postgres_query_readonly mixes verb/noun with an adjective. The pattern is readable but not uniform.

Tool Count5/5

Eight tools is a reasonable, focused set for an ops-oriented server spanning filesystem inspection, GitHub workflows, and read-only Postgres access. Each tool has a clear purpose and none feel redundant or superfluous.

Completeness4/5

The tool surface covers the main read-only investigation workflows: file lookup, GitHub issue triage and PR diff summaries, Postgres querying/explaining, and deployment status. Minor gaps exist such as no directory listing, no GitHub PR list endpoint, and no database schema introspection, but agents can work around these.

Maintenance

ActivitySlowing

ResponsivenessNo recent community issues

Resources

Related MCP Connectors

EphemeralA
al.ephemer
Run AI agent tasks in isolated sandboxes with a cost cap, saved workflows and scoped connections.
Agent Orchestration Autonomous Agents Code Execution
191
https://app.ephemer.al/mcp
QueryBear
io.github.spencerpauly
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Databases RAG Systems
2
https://mcp.querybear.com/mcp
Proofable MCPB
io.github.proofable
Context and control for any AI. Agent identity, scoped access, and proof across tools.
Security Agent Orchestration Autonomous Agents
3511
https://mcp.proofable.me/mcp
boundaryai
ai.boundaryai
Deterministic runtime safety for AI agents: scan PII, gate tool actions, verify LLM output.
Security AI & Machine Learning Agent Orchestration
2
https://mcp.boundaryai.ai/mcp

Related MCP Servers

GithubMCP
Version Control CI/CD & DevOps Code Analysis
Dhananjayrbiraris
A
license
A
quality
D
maintenance
Connects AI assistants to GitHub repositories, pull requests, issues, commits, and code search while enabling repository visibility controls, CI/CD monitoring, sandboxed local filesystem access, and code quality/security analysis.
Updated 3 months ago (2026-08-26 06:30 UTC)
13
1
MIT
Sandbox MCP
Code Execution Virtualization Developer Tools
Dhananjay-JSR
A
license
A
quality
B
maintenance
Enables AI coding agents to safely execute commands, run tests, and modify project files inside disposable, policy-enforced Docker sandboxes that are isolated from the host machine and its credentials.
Updated 2 months ago (2026-09-07 12:53 UTC)
15
MIT
enterprise-core
Databases Version Control ERP Systems
Muhammedali26
F
license
Not graded
quality
C
maintenance
Enables AI agents to investigate incidents by safely querying PostgreSQL, triaging GitHub issues, retrieving ERP order data, and sending Slack alerts, with AST-validated SQL and human-in-the-loop safeguards.
Updated 2 months ago (2026-09-09 10:47 UTC)
-
RepoMind
Code Analysis Version Control Developer Tools
TaherFetoui
A
license
Not graded
quality
C
maintenance
Enables AI coding assistants to inspect local and remote repositories through sandboxed tools that surface project overviews, structure, dependency audits, Git churn hotspots, and a heuristic health score. It also supports safe GitHub issue searching and creation with built-in duplicate preflight checks, while blocking sensitive files, binary content, and path traversal attacks.
Updated 2 months ago (2026-09-12 22:25 UTC)
22 npm
MIT

OpsMCP

Architecture

Tools

Safety

Stack

Run

Configuration

Verification flows

Spec

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

GithubMCP

Sandbox MCP

enterprise-core

RepoMind