Code-only MCP servers — agent-tools.cloud

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.

tablekit-mcp

github.com/Orange123Eleven/tablekit-mcp
active

Dependency-free MCP server for tabular data: convert markdown/CSV/TSV/JSON/HTML, re-align ragged Markdown tables (CJK-aware), transform and inspect tables.

MIT
jdatamunch-mcp

github.com/jgravelle/jdatamunch-mcp
active

Token-efficient MCP server for tabular data retrieval via CSV/Excel/Parquet/JSONL indexing

pypi LicenseRef-jDataMunch-Dual-Use
@krv-labs/pulsar

github.com/krv-labs/pulsar
active

Pulsar: topological data analysis for tabular data, as an MCP server and CLI.

npm BSD-3-Clause
pdf-writer-mcp

github.com/shuji-bonji/pdf-writer-mcp
active

MCP server that creates PDFs from text, Markdown, or tabular data and edits existing ones (metadata and page operations). Built on pdf-lib, with CJK font embedding via harfbuzz subsetting.

MIT
predictorlab

github.com/MarkIvor/predictorlab
active

Self-hosted tabular ML that doesn't lie. Leakage Guard, conformal intervals, profit-optimized thresholds, counterfactuals & instant REST/MCP API.

MIT ★ 8
jdatamunch-mcp

github.com/jgravelle/jdatamunch-mcp
active

Token-efficient MCP server for tabular data retrieval. Index CSV/Excel files, query rows, aggregate — 99%+ token savings vs raw file reads.

NOASSERTION ★ 83
geocluster-mcp

github.com/EigenformAI/geocluster-mcp
active

MCP server that gives LLM agents ~50 tools for exploration-geoscience data: inspection, cleaning, spatial ops, feature engineering, clustering, anomaly detection, and visualization for raster and tabular data.

Apache-2.0
QuickLab-MCP

github.com/Aldrin-Joan/QuickLab-MCP
active

Enterprise-grade Machine Learning experimentation control plane for AI agents via Model Context Protocol (MCP). Train, validate, and diagnose 7 tabular architectures (LightGBM, XGBoost, CatBoost, RF, SVM, MLP) with zero arbitrary code execution.

★ 1
token_optimizer

github.com/omkar9854/token_optimizer
updated this year

Zero-dependency, fully-reversible context compression for AI agents — cut LLM token usage up to 94% (JSON tabularization, log template mining, query-aware code skeletons). Stdlib-only, air-gap ready, built-in MCP server.

Apache-2.0 ★ 1
mcpbi

github.com/jonaolden/mcpbi
updated this year

PowerBI MCP server to give LLM clients (Claude, GH Copilot,etc) context from locally running PowerBI Desktop instances.

★ 22
mcp-engine

github.com/maxanatsko/mcp-engine
updated this year

SemanticOps MCP - Power BI MCP Server providing programmatic access to Power BI models via Model Context Protocol

npm SEE LICENSE IN LICENSE
mcp-engine-public

github.com/maxanatsko/mcp-engine-public
active

The SemanticOps MCP (formerly MCP Engine) is a Power BI tool that lets AI assistants like Claude interact with your Power BI models programmatically: read your model structure, run DAX queries, modify your semantic model, and perform advanced analytics - all through natural conversation.

NOASSERTION ★ 256