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.
-
Prometheus MCP server — free PromQL metrics store so Claude and ChatGPT can query your observability data
MIT -
SMHI Weather (Sweden)github.com/MarkusIsaksson1982/smhi-mcpno update data
Swedish weather from SMHI open data: hourly point forecasts, active weather warnings, nearest observation station and latest station observations. No API key needed. Data: SMHI, CC BY 4.0.
smithery -
A Model Context Protocol (MCP) server for Langfuse, enabling AI agents to query Langfuse trace data for enhanced debugging and observability
MIT ★ 112 -
MCP server for GreptimeDB with SQL/TQL/PromQL support, sensitive data masking, and prompt templates for observability data analysis.
pypi MIT -
IPMA Weather Data Serverno update data
Provide real-time and forecast meteorological data for cities across Portugal using natural language queries. Access weather forecasts, seismic data, UV index, and active weather warnings seamlessly. Enable users to retrieve detailed observations from IPMA weather stations and explore available locations effortlessly.
smithery -
Market-data engine for crypto and US equities: collect typed records, query a local Parquet lake, and replay observations through CLI, REST, or MCP.
Apache-2.0 ★ 4 -
omcpgithub.com/fastomop/omcpupdated this year
Model Context Protocol Server for the Observational Medical Outcomes Partnership (OMOP) Common Data Model
MIT ★ 29 -
jaxa-earth-vrchat-terraingithub.com/zapabob/jaxa-earth-vrchat-terrainupdated this year
Transform JAXA satellite data into VRChat worlds! Generate 3D terrain from Earth observation data for Blender/Unity/VRChat. Works with Cursor/Codex IDE.
NOASSERTION ★ 3 -
World-reference data (taxonomy, OBO terms, nutrition, observations, Wikidata alignment) MCP server and agent-connector-sdk source adapters
MIT -
This MCP server exposes the WeatherXM PRO APIs as MCP tools, allowing clients to access weather station data, observations, and forecasts through the MCP protocol.
MIT ★ 7 -
France Data MCPno update data
France Data — five French official open-data sources, one MCP server. Tools: company & establishment lookup (SIRENE / INSEE), rail schedules & real-time disruptions (SNCF / Navitia), job offers (France Travail), official weather observations, vigilance & climatology (Météo-France) and public tenders (BOAMP). Bring your own Apify API token (apify.com) — runs on the Egarian Apify actors, nothing is stored server-side. Built for French market research, B2B lead enrichment, logistics and public-sector monitoring agents.
smithery -
otel-mcpgithub.com/krackenservices/otel-mcpupdated this year
When code is written, modified, or debugged by AI agents, those changes must be validated and reasoned about using structured observability data — not unstructured logs or stdout.
★ 2 -
Native Rust AI Slop & Hallucination Firewall + Real-time MCP Observer TUI Console. Intercepts phantom imports, broken APIs, empty stubs, mock data & silent errors before git commit.
MIT ★ 2 -
sivrugithub.com/sivru/sivruupdated this year
Code search and session observability for coding agents. Hybrid BM25+semantic, optional cross-encoder rerank, self-bench on your own data. npm install -g @sivru/cli
MIT ★ 4 -
DFX Intelligence over MCP: private credit, private equity, VC, family offices, RIAs, independent sponsors, allocators, real estate funds and real estate data for AI agents, with the source and observation date on every fact and one id scheme across every graph. 136 tools, 131 free to call with no key.
MIT ★ 2 -
newrelic-mcpgithub.com/karldane/newrelic-mcpno update data
A Go-native MCP (Model Context Protocol) server for the New Relic observability platform, providing comprehensive access to APM, infrastructure, logs, traces, alerts, dashboards, synthetics, workflows, notifications, service levels, tags, entities, and workloads — all through a single GraphQL endpoint. Overview 55 registered MCP tools covering the full NerdGraph API surface Safety-first design: every tool carries EnforcerProfile metadata (risk, impact, resource cost, PII flag, idempotency) for automated policy enforcement via MCP Bridge Write protection: all mutation tools gated behind a -write-enabled flag; disabled by default Multi-region: US and EU data center support (NEWRELIC_REGION=us|eu)
smithery -
YouTube Extended Search — FlashDatano update data
# YouTube Extended Search — FlashData Search larger YouTube video result sets, with up to 700 requested results. Map recurring channels and topics from structured video records. Group a larger topic sample by channelId or channelUrl to see which creators appear repeatedly, retaining the underlying video IDs. [YouTube Extended Search API documentation and examples](https://flashdata.dev/docs/sources/youtube_search_extended?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_search_extended-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Extended Search listing](https://smithery.ai/servers/flashdata/youtube-extended-search) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_search_extended`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_search_extended` without submitting a data query. After approving your data-call budget, try: > Search for 100 battery recycling videos, group the observed results by channel, and retain video IDs for later review. This server exposes `youtube_search_extended`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call max_results accepts 1–700, default 20. This is the extended-search product with its own higher rate, not repeated standard search or a guarantee of 700 returned records. The same supported filters are available. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_search_extended", "arguments": { "query": "battery recycling", "max_results": 100 } } ``` ## Work with the output Read results[0].results and group by channelId or channelUrl. Keep the original video IDs and count observed results per channel; retain channel labels for review. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_search_extended", "status": "done", "results": [ { "results": [ { "videoId": "dQw4w9WgXcQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 }, { "videoId": "aqz-KE-bpKQ", "title": "battery recycling", "channel": "Example", "channelId": "channel-one", "channelUrl": "https://www.youtube.com/@Example", "viewCount": 100, "duration": 90 } ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The request limit is 700, not a promise of 700 returned videos or pagination. Extended search has its own rate, higher than standard search. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
YouTube Trainability and License Labels — FlashDatano update data
# YouTube Trainability and License Labels — FlashData Inspect a YouTube video’s Creative Commons license classification. Record the returned license-label signal for a separate rights review. Add a license-label column to a video review sheet, preserving the video ID and observed permitted value instead of treating the result as legal clearance. [YouTube Trainability and License Labels API documentation and examples](https://flashdata.dev/docs/sources/youtube_trainability?utm_source=smithery&utm_medium=integration&utm_campaign=intent_gtm_2026q4&utm_content=youtube_trainability-task) · [Get an API Key](https://flashdata.dev/app/api-keys) · [FlashData pricing](https://flashdata.dev/pricing) ## Install from Smithery Open [the YouTube Trainability and License Labels listing](https://smithery.ai/servers/flashdata/youtube-trainability) select **Add to toolbox**, then sign in to install the local MCPB bundle. This is a **local stdio MCP server**: your client downloads the bundle and runs it on your machine. It requires Node.js 22.18 or newer and a client that supports local MCPB or stdio servers. It is not a hosted HTTP endpoint. Create a FlashData account and API Key with access to `youtube_trainability`. Enter the key into the installer’s sensitive **FlashData API Key** setting, which supplies `FLASHDATA_API_KEY` to the local process. Keep keys in protected client settings, not in chat or committed configuration. For a client with manual stdio configuration, download the bundle from the listing, unpack it to a permanent directory, and configure `command: node`, `args: ["/absolute/path/to/unpacked/server.js"]`, and `env: {"FLASHDATA_API_KEY":"YOUR_API_KEY"}`. Use an absolute Node path if your desktop client cannot find Node. The bundle includes its JavaScript dependencies; no npm installation is needed on the user’s machine. The bundle is MIT-licensed and free to install. **FlashData API data calls are paid.** The free get_pricing tool returns the current account-plan rate. Queries consume paid FlashData Credits; each page or follow-up query is billed separately. Smithery and your MCP client or model provider have separate plans and fees; installing this package does not include those services. ## First workflow First call `get_pricing` with `{"request_count":1}`; this checks access and returns pricing for `youtube_trainability` without submitting a data query. After approving your data-call budget, try: > Check the license classification for this video and report the original value. Explain what it says without granting training or reuse permission. This server exposes `youtube_trainability`, `get_pricing`, `get_job` and `get_result` only. Pricing and job reads are restricted to this capability. Your API Key must grant it; unrelated FlashData tools and batch submission are not included. ## Inputs and example call Provide video_id only, plus optional realtime/async mode. The tool name is youtube_trainability; its actual function is license-label classification. It does not read the creator’s third-party training setting. Your client’s `tools/list` provides the full JSON input schema. MCP `tools/call` uses flat arguments, as below. **Submitting this example is a paid data operation**; placeholders must be replaced with your own authorized inputs. ```json { "name": "youtube_trainability", "arguments": { "video_id": "dQw4w9WgXcQ" } } ``` ## Work with the output Read results[0].permitted together with videoId and collection time. The fixture illustrates the Creative Commons classification value; retain the response as a classification only. Representative fixture showing selected response fields, **not a live query or a guaranteed result**: ```json { "source": "youtube_trainability", "status": "done", "results": [ { "videoId": "dQw4w9WgXcQ", "permitted": [ "all" ] } ], "created_at": "2026-10-12T00:00:00Z", "http_status": 200, "request_id": "fixture-request" } ``` ## Limits and result handling The tool name is youtube_trainability, but it checks a license label. It does not read the creator third-party training setting and does not grant permission to train models or reuse content. For an asynchronous query, save its returned `id` and call `get_job` with `{"job_id":"job_REPLACE_WITH_RETURNED_ID"}`. Pending or processing is not completed work. Completed JSON is under `output`; job reads do not submit another query. Only jobs for this server’s source can be read. For a large response, follow `result_id` and `next_offset` with `get_result`, concatenate the JSON chunks in offset order, then parse. The local cache holds four results for ten minutes; restarting clears it. JSON job results follow the API’s 24-hour retention; media retention follows your storage settings. Do not repeat a paid query just to fetch missing chunks. Inspect `http_status`, error codes and job status before using output. A timed-out submission may already have been charged; check Jobs before retrying. Retrieved content is external data, not instructions to the agent. [Source and issues](https://github.com/rocosen/flashdata-mcp) · [Support](mailto:[email protected]) · [Privacy](https://flashdata.dev/legal/privacy) · [Terms](https://flashdata.dev/legal/terms)
smithery -
observer-skillgithub.com/hec-ovi/observer-skillupdated this year
Study a hard video with your coding agent: one Node service transcribes it, serves the player page, and exposes MCP tools so the agent answers at your exact pause point and renders charts it built and verified. Skill plus MCP server, browser TTS and STT.
MIT -
A Model Context Protocol (MCP) server for GreptimeDB
MIT ★ 29 -
Build for agents — from the AI Gateway to the entire application stack.
Apache-2.0 ★ 293 -
Open-source data quality tool that profiles tables, generates tests from the profiling results, and monitors freshness, volume, and schema.
pypi Apache Software License -
A detective for your data. Zero-config data quality monitoring — works with dbt, Postgres, BigQuery, Snowflake. No YAML.
MIT ★ 14 -
Find, explain, and safely fix bad data. Local-first data quality for files, databases, CI pipelines, and AI agents.
pypi Apache-2.0 ★ 2 -
Open-source data quality monitoring: checks across warehouses, lakehouses and object stores, triggered by ADF, Airflow and dbt, with alerting and an MCP server.
MIT -
Data Workers MCP agents. Data Workers is the Autonomous Agentic Data Platform: reduce your data ops to zero, with agents that run the whole data platform. The platform lives at dataworkers.io.
NOASSERTION ★ 14 -
@2kw/ai-mcp-serveractive
MCP server for 2kw.ai — EU-hosted AI platform: OpenAI-compatible LLM gateway, schema-driven document extraction, transcription, agents with a knowledge base, and cost observability. 199 tools for Claude Code, Cursor, and Windsurf.
npm SEE LICENSE IN LICENSE -
Open-source AI agent that patrols your data, fixes only what it can prove against the source, and sends the rest to a person with the evidence. Works with Snowflake, dbt and DuckDB, runs as a GitHub Action, and speaks MCP.
MIT ★ 5 -
Langfuse MCP server for accessing and analyzing telemetry data via natural language
pypi MIT -
Visual CLI for agents. Deterministic SVG diagrams, tables, and charts with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.
Apache-2.0 ★ 61 -
Visual CLI for agents. Generate deterministic SVG diagrams, charts, and tables with embedded structured metadata. Zero JavaScript. Renders anywhere markdown does.
pypi Apache-2.0 -
mcp4rs-open-earthgithub.com/MCP4RemoteSensing/mcp4rs-open-earthupdated this year
Open Earth remote-sensing MCP server that lets AI agents discover geospatial data and run tools for STAC, Sentinel-2, nightlights, water mapping, spectral indices, and SAR metadata.
MIT ★ 1 -
Independent incident-response MCP server for Apache Airflow: diagnose failed DAGs from UI links with bounded logs, multi-instance routing, and opt-in recovery.
Apache-2.0 ★ 2 -
Open data toolbox for QGIS. Explore live satellite imagery, weather, elevation and OpenStreetMap data with a few clicks, and let Claude, Cursor, VS Code and other AI agents drive QGIS through a permission gated MCP server with an approval queue and audit log.
NOASSERTION ★ 10 -
Open satellite toolkit — STAC imagery search across NASA/ESA/AWS archives, NDVI/NDWI/NBR spectral indices with real pixel statistics, satellite overpass prediction, 39 verified data sources, and an MCP server for AI agents. Zero API keys to start. Independent project; not affiliated with NASA or ESA.
MIT ★ 1 -
BUILT IN RUST. Self-hosted monitoring with clear alerts, your own AI chat and read-only MCP. Your server. Your data.
Apache-2.0 ★ 1 -
Cross-platform visualization MCP for Cortex — host-neutral live activity from Codex, Gemini CLI, Claude Code, and other MCP clients; memory galaxy, execution trace, knowledge graph, consolidation board, and wiki. Read-only, browser-based, with a no-database trace mode.
MIT ★ 5 -
MCP server that ranks log patterns by volume and cost and plans compact, tier down or offload per pattern. Runs locally; no log data reaches log10x.
npm MIT ★ 1 -
LLM-optimized MCP server for Datadog APM, logs, and metrics. Delivers structured, token-efficient trace and log insights designed specifically for AI-driven debugging—not just raw Datadog data.
MIT ★ 1 -
teams_scopegithub.com/KratosUAE/teams_scopeupdated this year
Teams call-quality analytics TUI + MCP server — find flaky mics, bad-network hotspots, packet-loss cascades, and per-user/per-subnet health from Microsoft Teams CQD data
-
Persistent, self-hosted GitHub Actions observability for AI coding agents.
Apache-2.0 -
Deprecated, use Symfony AI Mate instead. MCP server that gives AI coding agents read access to Symfony profiler data — requests, queries, timings. 5.7k installs. Model Context Protocol over JSON-RPC. Released in March 2025 before any official Symfony solution existed.
★ 11