MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
Koalr MCP server — connect engineering metrics to AI agents
npm MIT -
MCP server that gives engineering leaders quality KPIs (MTTR, DORA metrics, defect escape rate, SLA breaches) from Jira and incident exports.
MIT -
startup-finance-metricsgithub.com/MayankTalwar0/startup-finance-metricsupdated this year
Financial metrics engine and MCP server for startups.
pypi MIT -
Open-source engineering intelligence: ingests real development events, computes metrics with published contracts, detects change against each scope's own history, and decomposes what accounts for it. Never fabricates a number.
Apache-2.0 -
Connect to your Jellyfish Software Engineering Intelligence platform for comprehensive team insights, effort allocation, and delivery metrics.
npm MIT -
@flowdna/mcpgithub.com/rekyli198/flowdnaupdated this year
MCP (Model Context Protocol) bridge for FlowDNA — query your engineering metrics from Claude Desktop, Cursor, or any MCP-aware tool.
npm Apache-2.0 -
MCP server for converting technical drawings (PDF) and engineering callouts between metric and imperial — dimensions, fits, tolerances, threads, surface roughness.
npm MIT -
health-enginegithub.com/a-deal/health-engineupdated this year
Open-source health scoring engine — 20 clinically validated metrics, NHANES percentiles, wearable integration. Runs locally with Claude via MCP.
pypi MIT -
Your business data, explained by an ape — a semantic-layer engine for business metrics, exposed as an MCP server.
MIT -
craftquantities-engineactive
The Craft Quantities engine as a local MCP server over stdio: construction quantities from cited calculators, takeoffs, planners, drawings and cut plans, in metric and US units. No prices; nothing sized.
npm SEE LICENSE IN LICENSE.md -
Give humans and AI agents the same map of your codebase: dependency graph, complexity and code-smell metrics, MCP server. Ten languages, Rust engine, VS Code + CLI.
AGPL-3.0 -
Koalr MCP server — connect engineering metrics and deploy risk to Claude, Cursor, and Windsurf
MIT -
Agentic-Code-Reporting-MCP-Servergithub.com/shlokkakde/Agentic-Code-Reporting-MCP-Serverupdated this year
Agentic Code Intelligence Engine — MCP server that converts Git history into stakeholder-ready engineering reports with 18+ productivity metrics
-
Madjik MCP server — quantum-finance market metrics for AI agents, computed by the Black Belt Labs engine. npm: madjik-mcp-server
npm MIT -
AI-powered engineering-ops platform: service monitoring, metrics, and incident management, exposed to Claude via MCP.
MIT ★ 7 -
pptx-mcp-servergithub.com/knorq-ai/pptx-mcp-serverupdated this year
Content-aware PPTX layout engine with Japanese-aware text metrics, CSS-flex-like primitives, and structural validator for agent-generated consulting decks
pypi MIT -
AI/ML-powered diagnostic engine for SRE Observability on Konflux and OpenShift. It uses the Model Context Protocol (MCP) and 40+ tools to analyze logs, metrics, and traces, enabling automated RCA and predictive analysis.
pypi Apache-2.0 ★ 11 -
Turn your Readwise library into a blazing-fast, self-hosted semantic search engine – complete with nightly syncs, vector search API, Prometheus metrics, and a streaming MCP server for LLM clients.
MIT ★ 24 -
Home Assistant app: authenticated ingestion API, event store, feature engineering, coverage metrics and a read-only MCP server for Android timeline data. Experimental.
MIT -
payments-reliability-copilot-mcpgithub.com/mr-azharul/payments-reliability-copilot-mcpupdated this year
MCP server that exposes AI copilot tools for diagnosing payment transaction failures, computing reliability metrics, and suggesting optimizations. Payments engineers and fintech developers use it to monitor success rates, analyze error patterns, and prevent downtime in processing pipelines.
-
Local-first AI resume tailoring engine with deterministic zero-token fact verification, MCP server integration, and sub-30ms Typst WASM PDF compilation. No hallucinations, altered metrics, or broken formatting.
npm MIT ★ 2 -
MCP agent for semantic metrics governance with built-in trust scoring, lineage visualization, and conversational metric definition. Designed for data teams working with dbt, LookML, and modern semantic layers.
★ 5 -
-semantic-metrics-modeling-assistantgithub.com/venugopal743/-semantic-metrics-modeling-assistantupdated this year
MCP agent for semantic metrics governance with built-in trust scoring, lineage visualization, and conversational metric definition. Designed for data teams working with dbt, LookML, and modern semantic layers.
★ 1 -
One governed metric contract, many consumers: validator CLI, MCP server, chart meaning gate, decomposition check.
pypi Apache-2.0 -
A metric registry an agent has to go through: definitions in YAML, SQL from dbt, and every number in an answer checked against the result it came from.
MIT -
Self-hosted engineering-operations analytics for small software teams: delivery, cost and risk, drillable to the source record. FSL-1.1-ALv2, Apache 2.0 after two years.
NOASSERTION ★ 2 -
A governed GA4 semantic layer in dbt + MetricFlow on BigQuery, queryable by humans and by LLM agents over MCP. The README is a metric definition document: every metric states its definition, assumption, trade-off and failure mode.
MIT -
Toolkit and MCP server for auditing AI coding assistant productivity in engineering sprints
MIT ★ 1 -
AIEI: AI Effectiveness Index - CLI and MCP
npm MIT -
Deterministic SaaS accounting, SEC XBRL revenue quality and point-in-time FP&A backtesting: billing adapters, DuckDB engine, audited Excel models, Streamlit workbench and MCP server.
MIT -
mcp-sonarqubegithub.com/viamus/mcp-sonarqubeupdated this year
MCP for SonarQube that analyzes code quality, technical debt, vulnerabilities, and coverage, enabling AI-driven engineering insights.
MIT ★ 2 -
Prumi server: MCP endpoint, catalog, query engine, validator and registry
pypi Apache-2.0 -
Visual end-to-end map of API, gRPC and database contracts with system-design checks, breaking-change diffs and AI-coding-agent impact analytics. CLI, web UI and MCP server.
NOASSERTION -
Map every feature and user flow in a codebase from git history and code structure. No Jira, no annotations. Bug hotspots, health scores, symbol-level attribution and an MCP server for AI coding agents.
NOASSERTION -
A semantic layer that refuses to answer wrongly. Compiles Apache Ossie models into governed, dialect-correct SQL, and declines the joins that would silently inflate a total. Self-hosted, MCP for agents, JSON over HTTP for everything else.
Apache-2.0 ★ 1 -
A comprehensive Kubernetes observability toolkit built on the Model Context Protocol (MCP) for Site Reliability Engineering.
★ 2 -
Metis turns agent intent into governed, reproducible, engine-neutral queries over shared semantic assets through semantic discovery, resolution, validation, planning, and compilation.
go Apache-2.0 ★ 4 -
Read-only MCP server + Claude Code plugin for investigating data quality issues: metric drops, duplicates, joins, freshness, dbt test failures.
MIT -
airflow-monitor-mcpgithub.com/RakhaHafishSetiawan/airflow-monitor-mcpupdated this year
An MCP server built with FastMCP to monitor, log, and analyze airflow data. Brings real-time environmental metrics directly to your LLM tools.
MIT ★ 1 -
Payment-risk triage with logistic regression, held-out precision metrics, grounded LLM decisions, bounded RAG prompts, audit storage, MCP and Docker.
MIT -
Census ACS to DuckDB to tested dbt marts to governed metrics, served by a read-only MCP server AI agents can query safely.
NOASSERTION -
Messy retail data turned into trusted metrics with dbt, plus an AI analyst that answers from them (40/40)
MIT -
Readiness system that lets AI agents build your BI pipeline but never approve it -- evidence-gated source profiling, medallion mappings, metric contracts, and Power BI delivery. Offline demo in 60 seconds: uvx --from seshat-bi seshat demo init
npm Apache-2.0 ★ 2 -
flowproxygithub.com/dbose/flowproxyupdated this year
Self-hosted dbt-core + MetricFlow semantic layer proxy. Query governed metrics from Amazon QuickSight and LLM agents over the PostgreSQL wire protocol, with guardrails enforced. Air-gapped, no dbt Cloud, no custom drivers.
Apache-2.0 -
Creator growth intelligence lakehouse: quota-aware YouTube ingestion, DuckLake bronze, dbt marts, Dagster orchestration, a five-page Streamlit product, 10 SLO checks, and a governed MCP metric server.
MIT -
Test data management: format-preserving masking, referential subsetting, privacy metrics, audit lineage, and a CI release gate. Python and FastAPI.
MIT ★ 1 -
Ask your data. Get answers your team has verified. Open-source analytics workbench where every answer is labelled Certified, From Metrics or Needs review. Works on your dbt project or straight on your database, with lineage, Apps and an MCP server for Claude, Codex and Cursor.
Apache-2.0 ★ 2