SkillFoxx

flowR MCP

flowR MCP gives an agent static analysis of R code: slicing, linting, dependencies, version guessing and signature search.

  • 108 ★ on the repository
  • Last commit
  • GPL-3.0
MCP serverOfficial

Extended access

Why this level

  • The first start downloads the signature database from the network; the server never runs analyzed code.
All reasons and checks

flowr-analysis/flowrAuthor:flowr-analysis

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add mcp/flowr-mcp

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The first start downloads the signature database from the network; the server never runs analyzed code.

This is third-party code. Review the repository files before installing.

What it does

flowR is a static dataflow analyzer for the R language. Its MCP server lives in the `mcp/` folder of the repository and gives the agent one tool, `query`. Through it every flowR query is reachable: program slicing, linting, project dependencies, library version guessing, signature database search and the rest of the Query API. An R installation is not needed. The server never runs the analyzed code. On first start it downloads the signature database, about 66 MB, from the flowR releases into `~/.cache/flowr` and checks its hash. Everything else also works offline. For Claude Code a plugin installs the server together with the flowR skill.

Who it is for. Analysts and researchers writing in R who ask an agent to make sense of foreign scripts, dependencies and dataflow.

Good fit when

  • You must learn which libraries and data files a foreign R project needs.
  • An agent slices a program to find where a variable value comes from.
  • A linter has to check scripts without running them.
  • For reproducibility you must guess the allowed package versions.

Not a fit when

  • The code is not in R.
  • You must run the code and see the result: the analysis is static only.
  • The network is closed yet you need package versions and signature search: they need the downloaded database.

Example request

Find out which packages and data files this R project uses and guess the allowed package versions.

MCP

Transport
stdio, http
Authentication
not required

Environment variables

FLOWR_MCP_PATH secret
Secret path replacing `/mcp` in HTTP mode.

Limitations

The first start downloads about 66 MB of the signature database and checks its hash, and it is required for package versions and signature search. A linter query with `checkUrls` visits addresses found in the code, and that mode is refused over HTTP. In HTTP mode the server treats code as untrusted, and remote clients need an HTTPS address: the README shows a `cloudflared` tunnel. A secret `FLOWR_MCP_PATH` is the only access control that every remote client supports.

How to disable. Run `/plugin uninstall flowr` or `claude mcp remove flowr`. Delete the signature database cache from `~/.cache/flowr`.

FAQ

How do I install flowR MCP in Claude Code?

Through the plugin: `/plugin install flowr --marketplace flowr-analysis/flowr`, which installs both the server and the skill. Or `claude mcp add flowr -- npx -y --omit=optional --ignore-scripts @eagleoutice/flowr-mcp`.

Do I need R installed?

No. flowR analyzes code statically and runs nothing itself.

What do the `--omit=optional` and `--ignore-scripts` flags do?

They keep the install small by skipping optional dependencies and install scripts. Every dependency is pinned in `npm-shrinkwrap.json`.

How do I connect the server to ChatGPT or claude.ai?

Run `npx -y --omit=optional --ignore-scripts @eagleoutice/flowr-mcp --http 1042`, expose the port over HTTPS and add `https://<host>/mcp` as a connector.

What licences do flowR and the MCP plugin use?

The main repository is GPL-3.0, while the MCP plugin manifest declares ISC.

Discussion

No questions or reviews yet.

MCP servers

MCP server that connects Claude Code and Codex to an open R or Python session in RStudio and Positron, where your data lives

MCP serverBroad access372
Official

The official Graphlit MCP server: an agent collects material from Slack, GitHub, mail and websites into a knowledge base and searches it

MCP serverBroad access379

MCP server for the Flexible GraphRAG platform: ingest from 14 data sources, hybrid search and AI answers over a knowledge graph

MCP serverBroad access200
Official

MCP server and skills for product analytics: user paths, funnels, segments and transition graphs over event logs

MCP serverExtended access947
Official

The hosted Roboto MCP server lets an agent search a robot fleet's datasets and files and analyze topic data without changing them

MCP serverExtended access58

README in short

The main repository presents flowR as an analyzer for VS Code, Positron, RStudio and Docker. The MCP server is a separate `@eagleoutice/flowr-mcp` package with its own README and skill.

README badge

Report a problem