Enables AI clients to perform static dataflow analysis, program slicing, linting, and dependency extraction for R code.
Also known as flowr-analysis/flowr, @eagleoutice/flowr-mcp
- Stars
- 108
- Tools
- 1
- Downloads, 30 days
- 1,000
- Latest version
- 0.1.4
- Last commit
- Nov 15, 2026
- License
- GPL-3.0
What is flowR MCP?
flowR enables AI clients to perform static dataflow analysis, program slicing, linting, and dependency extraction for R code. It exposes 1 tool, such as query.
Summary generated from the project's README
About flowR MCP server
flowR provides a single query tool that allows AI clients to perform deep analysis on R code without requiring a local R installation. It enables developers to execute tasks such as program slicing, linting, dependency extraction, and version guessing. The server operates by downloading a 66 MB signature database to the ~/.cache/flowr directory during its initial startup to support signature searches and version detection.
Users can run this server locally via stdio for clients like Claude Code, OpenAI Codex, or Gemini CLI, or configure it through JSON for desktop applications like Cursor and VS Code. For remote clients such as ChatGPT, the server must be hosted over HTTPS. When running over HTTP, the server operates in a secure mode that treats code as untrusted, limiting memory usage to 2 GB and cutting responses at 50,000 characters to maintain safety.
What you can do with it
- 1Identify R versionsDetermine which version of R a piece of code is intended for.
- 2Lint R scriptsCheck R code for stylistic or structural errors using the built-in linter.
Written from the project's README. Every use case is checked against a quote from it.
How to install flowR MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall flowR MCP in Claude Code
$ claude mcp add flowr -- npx -y @eagleoutice/flowr-mcpInstall flowR MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"flowr": {
"command": "npx",
"args": [
"-y",
"@eagleoutice/flowr-mcp"
]
}
}
}Install flowR MCP in VS Code
.vscode/mcp.json
{
"servers": {
"flowr": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@eagleoutice/flowr-mcp"
]
}
}
}Install flowR MCP in VS Code CLI
$ code --add-mcp '{"name":"flowr","type":"stdio","command":"npx","args":["-y","@eagleoutice/flowr-mcp"]}'Install flowR MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"flowr": {
"command": "npx",
"args": [
"-y",
"@eagleoutice/flowr-mcp"
]
}
}
}Install flowR MCP in Codex
$ codex mcp add flowr -- npx -y @eagleoutice/flowr-mcpInstall flowR MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.flowr] command = "npx" args = ["-y", "@eagleoutice/flowr-mcp"]
Install flowR MCP in Gemini CLI
$ gemini mcp add -s user flowr npx -- -y @eagleoutice/flowr-mcpInstall flowR MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"flowr": {
"command": "npx",
"args": [
"-y",
"@eagleoutice/flowr-mcp"
]
}
}
}Started by HostedMCP on 16 Nov 2026
We ran this command for @eagleoutice/flowr-mcp 0.1.4 in an isolated container with no network and no keys. It answered and listed 1 tool.
flowR MCP tools 1
Read from the server with tools/listqueryRead-onlyStatically analyze R code and search R package signatures with flowR queries (https://github.com/flowr-analysis/flowr/wiki/Query-API). Common ones: {"type":"static-slice","criteria":["12@x"]} for the code affecting x in line 12, {"type":"linter"} for lint findings, {"type":"dependencies"} for loaded libraries, read and written files, {"type":"guess-dep-versions"} for the package versions the code works with, {"type":"call-context","callName":"^read_"} for calls, and, needing no code, {"type":"signature","package":"dplyr","function":"across"} to search signatures and versions (globs allowed), {"type":"function-info","name":"filter"} for the packages exporting a function. A query with wrong arguments is answered with its schema. Types: call-context (Call-Context Query), config (Config Query), control-flow (Control-Flow Query), call-graph (Call-Graph Query), dataflow (Dataflow Query), does-call (Does-Call Query), dataflow-lens (Dataflow Lens Query), absint (Abstract Interpretation Query), files (Files Query), id-map (Id-Map Query), normalized-ast (Normalized AST Query), dataflow-cluster (Dataflow Cluster Query), static-slice (Static Slice Query), provenance (Provenance Query), input-sources (Input Sources Query), dependencies (Dependencies Query), location-map (Location Map Query), search (Search Query), happens-before (Happens-Before Query), inspect-exception (Inspect Exceptions of Functions Query), inspect-higher-order (Inspect Higher-Order Functions Query), inspect-recursion (Inspect Recursive Functions Query), inspect-fn-props (Inspect Argument Roles Query), resolve-value (Resolve Value Query), project (Project Query), signature (Signature Query), origin (Origin Query), linter (Linter Query), dice (Dice Query), guess-dep-versions (Guess Dependency Versions Query), function-info (Function Info Query)
| query | Statically analyze R code and search R package signatures with flowR queries (https://github.com/flowr-analysis/flowr/wiki/Query-API). Common ones: {"type":"static-slice","criteria":["12@x"]} for the code affecting x in line 12, {"type":"linter"} for lint findings, {"type":"dependencies"} for loaded libraries, read and written files, {"type":"guess-dep-versions"} for the package versions the code works with, {"type":"call-context","callName":"^read_"} for calls, and, needing no code, {"type":"signature","package":"dplyr","function":"across"} to search signatures and versions (globs allowed), {"type":"function-info","name":"filter"} for the packages exporting a function. A query with wrong arguments is answered with its schema. Types: call-context (Call-Context Query), config (Config Query), control-flow (Control-Flow Query), call-graph (Call-Graph Query), dataflow (Dataflow Query), does-call (Does-Call Query), dataflow-lens (Dataflow Lens Query), absint (Abstract Interpretation Query), files (Files Query), id-map (Id-Map Query), normalized-ast (Normalized AST Query), dataflow-cluster (Dataflow Cluster Query), static-slice (Static Slice Query), provenance (Provenance Query), input-sources (Input Sources Query), dependencies (Dependencies Query), location-map (Location Map Query), search (Search Query), happens-before (Happens-Before Query), inspect-exception (Inspect Exceptions of Functions Query), inspect-higher-order (Inspect Higher-Order Functions Query), inspect-recursion (Inspect Recursive Functions Query), inspect-fn-props (Inspect Argument Roles Query), resolve-value (Resolve Value Query), project (Project Query), signature (Signature Query), origin (Origin Query), linter (Linter Query), dice (Dice Query), guess-dep-versions (Guess Dependency Versions Query), function-info (Function Info Query) | Read-only |
Automated checks
Ran Nov 16, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachableflowr-analysis/flowr is public and reachablegithub.com/flowr-analysis/flowr ↗Pass
- Package names this repository as its source@eagleoutice/flowr-mcp names flowr-analysis/flowr as sourcenpmjs.com/package/@eagleoutice/flowr-mcp ↗Pass
- Build provenance (Sigstore attestation)Sigstore attestation for @eagleoutice/flowr-mcpnpmjs.com/package/@eagleoutice/flowr-mcp/v/0.1.4#provenance ↗Pass
- Open source license (OSI)GPL-3.0spdx.org/licenses/GPL-3.0.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-15github.com/flowr-analysis/flowr ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @eagleoutice/flowr-mcpPass
- No critical advisory in the package or its dependenciesthe package checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model1 tool description and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubflowR MCP Server
A Model Context Protocol server with a single query tool that lets LLM
clients analyze R code with flowR: slicing, linting, dependencies,
version guessing, signature database search, and every other query of the
Query API. No R installation is needed.
On its first start, the server downloads flowR's signature database (about 66 MB) from the
flowR releases into ~/.cache/flowr and checks its hash.
Version guessing and signature search need this database. Everything else also works offline. The server never
runs the analyzed code. It contacts no other server, unless a query asks the linter to check the URLs in the code
(checkUrls, which is never allowed over HTTP).
In Claude Code, one plugin installs both this server and the flowR skill:
/plugin install flowr --marketplace flowr-analysis/flowr
Other local clients start it over stdio:
claude mcp add flowr -- npx -y --omit=optional --ignore-scripts @eagleoutice/flowr-mcp # Claude Code
codex mcp add flowr -- npx -y --omit=optional --ignore-scripts @eagleoutice/flowr-mcp # OpenAI Codex
gemini mcp add flowr npx -y --omit=optional --ignore-scripts @eagleoutice/flowr-mcp # Gemini CLI
or, configured by JSON (Claude Desktop, Cursor, VS Code, ...):
{ "mcpServers": { "flowr": { "command": "npx", "args": ["-y", "--omit=optional", "--ignore-scripts", "@eagleoutice/flowr-mcp"] } } }
The flags keep the install small. They skip the optional dependencies flowR does not need here, and they run no
install scripts. The package's npm-shrinkwrap.json pins every dependency.
Remote clients (ChatGPT, claude.ai, ...) need the server running over HTTP behind HTTPS:
npx -y --omit=optional --ignore-scripts @eagleoutice/flowr-mcp --http 1042
cloudflared tunnel --url http://localhost:1042
Then add https://<host>/mcp as a connector (in ChatGPT, this needs developer mode). Without a port, the server
uses $PORT or 1042. It listens on 127.0.0.1 unless HOST says otherwise, for example HOST=0.0.0.0 in a
container. Setting FLOWR_MCP_PATH=/mcp/<random> replaces /mcp with a secret path. A secret path is the only
access control that every remote client supports.
Over HTTP, the server treats the code as untrusted:
- It never reads its own files: there is no
filesargument,source()is ignored, and theconfigquery is refused. - It runs in flowR's secure mode, without network access, processes, or R.
- It keeps stack traces to itself.
- It refuses requests from browser pages and requests over 1 MB.
- It runs one analysis at a time, with at most 16 waiting, and stops each after 30 seconds or 2 GB of memory.
- It cuts answers at 50000 characters.
Put a rate limit in front of a public instance.
SKILL.md is an agent skill (Claude, Codex, Gemini CLI, ...) that says when and how to use flowR,
with or without this server. To use it, copy it to, for example, ~/.claude/skills/flowr/SKILL.md.
flowR MCP questions
How do I add flowR MCP to Claude Code?
Run claude mcp add flowr -- npx -y @eagleoutice/flowr-mcp in your terminal. Add --scope user to make it available in every project.
How do I add flowR MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does flowR MCP provide?
It exposes 1 tool, including query.
Do I need to have R installed to use this server?
No, an R installation is not required to use the server.
Does the server run the R code being analyzed?
No, the server performs static analysis and never executes the analyzed code.
Does the server require an internet connection?
It requires an initial download of a signature database, but most features work offline.