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.
-
Governance-first Data Agent with Metric Wiki, Text-to-Metrics/Text-to-SQL routing, hybrid RAG, MCP, Skills and human approval.
MIT -
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 -
Governed gateway giving people and AI agents one definition of every business metric: YAML semantic view, Pydantic and NetworkX validation, sqlglot SQL compiler, FastAPI REST and MCP-style tools, React UI prototype
MIT -
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 -
MCP server for querying Graphite metrics from AI agents: browse, search and summarise graphite-web time series
npm MIT -
-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 -
Private equity & private markets fund performance metrics for .NET: TVPI, DPI, RVPI, MOIC, XIRR, PME (Kaplan-Schoar, Long-Nickels, PME+, mPME), Direct Alpha, vintage quartiles and J-curves. Zero dependencies, tested against Python references, with an MCP server for AI agents.
MIT ★ 1 -
dbt-agent-layergithub.com/dbt-agent-layer/dbt-agent-layerupdated this year
Make your dbt metrics queryable by AI agents via MCP
pypi Apache-2.0 -
pulse-mcpgithub.com/patwalls/pulse-mcpupdated this year
MCP server for Pulse — free, agent-first social-post metrics (YouTube, X, TikTok, Bluesky, Mastodon, Instagram, LinkedIn). Tools: metrics, metrics_batch, history, profile, profile_batch.
npm MIT -
Koalr MCP server — connect engineering metrics to AI agents
npm MIT -
MCP integration for AgentPulse: server card generation and an MCP tool server exposing agent traffic metrics.
npm MIT -
MCP server for AI agents to investigate OpenTelemetry traces, metrics, and logs
npm Apache-2.0 -
MCP server for EzStat (ezstat.dev) — let Claude, Cursor, and any MCP agent track and query metrics natively
npm MIT -
mcp-observabilitygithub.com/zavora-ai/mcp-observabilityupdated this year
Observability MCP Server — logs, traces, metrics, alerts, dashboards, incidents, SLOs, and runbooks for AI agents
cargo Apache-2.0 -
mcp-analyticsgithub.com/zavora-ai/mcp-analyticsupdated this year
Governed Analytics MCP Server — metrics, dashboards, funnels, cohorts, anomalies, forecasting, and policy enforcement for AI agents
cargo Apache-2.0 -
OpenTelemetry MCP Server — expose traces, metrics, logs, and ZK proofs to AI agents via the Model Context Protocol
npm Apache-2.0 -
CLI for querying and pushing time-series metrics. Works with Trifle App API or local databases. MCP server mode for AI agents.
NOASSERTION ★ 1 -
qorrelate-mcp-servergithub.com/sethmichaelking/arqiveupdated this year
MCP server for Qorrelate observability platform - 123 tools for AI agents to manage logs, traces, metrics, session replays, and alerts
npm MIT -
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 -
Open-source deterministic analytics harness for AI agents. Connect your warehouse, define business metrics in code, and let MCP agents query them — plus permitted raw warehouse columns, clearly labeled.
npm Apache-2.0 -
mcp-datadoggithub.com/viamus/mcp-datadogupdated this year
A Datadog MCP implemented in C# that exposes logs, metrics, traces, and monitors as structured context for AI agents, enabling automated observability analysis, test validation, incident investigation, and operational insights.
MIT ★ 5 -
Open-source semantic layer with an ontology at its core: governed metrics and business rules for AI agents (MCP), the same number on eight databases, with evidence on every answer.
pypi Apache-2.0 ★ 1 -
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 -
Auditable, local-first data & AI dataset workbench: multimodal evidence, traceable metric Q&A, and human-approved Agent/MCP actions.
Apache-2.0 ★ 156 -
Natural-language Hadoop cluster management via MCP. Connect LLM agents (Claude, GPT, etc.) directly to Apache Ambari REST API — control services, inspect configs, query metrics, and manage alerts with AI. Built with FastMCP & aiohttp.
MIT ★ 1 -
MoleSignal on the command line: logs, metrics, traces, incidents and approvals, deployments, source maps and symbols from CI, and MCP over stdio for AI agent tools
npm Apache-2.0 -
Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.
npm Apache-2.0 ★ 100 -
mcp-cloudwatch-explorergithub.com/sarteta/mcp-cloudwatch-explorerupdated this year
MCP-native CloudWatch metrics explorer. Lets AI agents query AWS CloudWatch metrics, alarms, and logs over MCP. Read-only by design.
MIT ★ 1 -
Portfolio of Li ZhenXi (SRE, cloud and AI infrastructure), run as a production service: Go on Cloud Run with its own live SLO, an MCP server for AI agents, OpenTelemetry traces, DORA metrics and build-once keyless deploys; Next.js and Terraform
MIT ★ 1 -
Allows AI assistants such as Amp/Cline/Cursor/Claude Code/Codex/GitHub Copilot to use Google's lighthouse tool to measure perf metrics for your webpage. You can then run an agentic loop and get the assistants to optimize those metrics!
npm MIT ★ 219 -
MCP server for agentic advertising intelligence. 7 tools: agent discovery, protocol metrics, deployments, compatibility, stack recommendations.
NOASSERTION -
@macroaxis/api-mcpactive
Macroaxis MCP server for AI agents: financial data, fundamentals, analyst ratings, ESG, earnings, dividends, price history, technical indicators, risk metrics, peers, ownership, forecasts, and portfolio correlation, optimization, metrics, and efficient fr
npm MIT -
metabase-agent-mcp-serverupdated this year
MCP server for the Metabase Agent API — discover tables, metrics, and execute queries against Metabase's semantic layer
npm MIT -
toolstem-mcp-servergithub.com/toolstem/toolstem-mcp-serverupdated this year
Agent-ready financial intelligence MCP tools — stock snapshots, company metrics, derived signals
go MIT ★ 1 -
MCP server that cleans messy Stripe and bank exports and serves financial metrics to AI agents
-
Local-first memory and policy service for AI agents: durable events, retrieval, portable handoffs, async jobs and operational metrics. Repository contact: Robin Winters.
MIT ★ 1 -
@luneo/mcp-servergithub.com/luneo19/luneo-platformupdated this year
Model Context Protocol server for Luneo — let AI agents (Claude Desktop, Cursor, Zed) pilot Luneo agents, conversations, metrics.
npm 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
-
@trulayer/mcpgithub.com/trulayer/client-typescriptupdated this year
TruLayer MCP server — read-only agent access to traces, evals, and metrics
npm MIT -
Madjik MCP server — quantum-finance market metrics for AI agents, computed by the Black Belt Labs engine. npm: madjik-mcp-server
npm MIT -
@nexusforgetools/social-intelgithub.com/nexusforge-toolsupdated this year
Social media intelligence — trend detection, sentiment, influencer metrics, viral content. MCP server for AI agents.
npm MIT -
@nexusforgetools/crypto-intelgithub.com/nexusforge-toolsupdated this year
Crypto intelligence — on-chain analytics, whale tracking, DeFi yields, token metrics. MCP server for AI agents.
npm MIT -
Bring your data platform to AI agents — an open MCP server exposing metadata, lineage, and metrics as first-class agent tools
MIT -
Keyword Metrics and modeled AI search demand for AI agents. Google Ads volume, CPC and question-demand signals via approved x402 calls.
npm MIT -
opsorch-mcpgithub.com/OpsOrch/opsorch-mcpupdated this year
MCP server for OpsOrch. Exposes OpsOrch incidents, logs, metrics, services, and tickets as safe, typed MCP tools for any LLM or AI agent.
Apache-2.0 ★ 2 -
MCP server for the GitHub Projects v2 API - views, priorities, dependencies, and metrics as typed tools for LLM agents
npm MIT ★ 1 -
Local MCP coding agent for ChatGPT Web: run files/commands on your own machine via the OpenAI Secure Tunnel, with a Windows tray app and metrics dashboard.
AGPL-3.0 ★ 59 -
MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power
go Apache-2.0 ★ 15 -
MCP server that gives LLM agents Oxford Nanopore QC tools — read, alignment, coverage & variant metrics via nanoq/cramino/mosdepth/samtools/bcftools, plus IGV snapshots.
MIT -
product-analytics-agentgithub.com/Michaela2024/product-analytics-agentupdated this year
AI agent that answers product analytics questions conversationally — queries metrics, compares segments, detects anomalies, and generates charts using Claude and MCP
-
Self-hosted OTLP observability in a single Go binary. Traces, logs, metrics, GraphRAG root-cause, MCP for AI agents.
MIT ★ 1 -
supportdesk-mcpgithub.com/marilynceo/supportdesk-mcpupdated this year
Zendesk ticket management for AI agents u2014 create, search, update tickets, list views, get SLA metrics, and add internal notes. First MCP server for helpdesk automation.
-
Embeddable .NET framework for longitudinal reporting: metrics → composable transforms → chart-agnostic views, with pluggable caching and an MCP agent surface.
nuget MIT -
streamops-agentgithub.com/atomicdragonranch/streamops-agentupdated this year
AI-powered operations agent for Apache Flink streaming pipelines. Monitors Kafka and Flink metrics, detects anomalies, and recommends scaling and configuration actions via an MCP server interface.
MIT ★ 1 -
Incident-investigation chat agent on Amazon Bedrock AgentCore Runtime, with a live-streaming UI and its own MCP server for per-prompt cost/token/tool-call metrics
MIT ★ 2 -
sre-agentgithub.com/benmoggee/sre-agentupdated this year
SRE Agent — An AI-powered MCP server for production incident triage. Takes natural-language symptom reports, plans structured investigations using Gemini, executes parallel workers (logs, metrics, deploys, runbooks), synthesizes root-cause reports, and proposes remediation patches with human approval gates.
MIT ★ 39 -
Codebase analysis MCP server for AI agents: complexity metrics, size thresholds, prop drilling, and code smell detection built on tree-sitter and tokei.
npm MIT ★ 1 -
Census ACS to DuckDB to tested dbt marts to governed metrics, served by a read-only MCP server AI agents can query safely.
NOASSERTION -
vertica-mcpgithub.com/zaboura/vertica-mcpupdated this year
Production-ready MCP server for Vertica—secure tools, row streaming, pagination, and system metrics for LLM agents (Claude, Cursor, VS Code).
pypi Apache-2.0 -
Scout’s local MCP puts metrics, traces and errors right in your AI agent. For teams that do it all.
pypi MIT ★ 30