manykarim/rf-mcp
manykarim/rf-mcp has 118 GitHub stars and 22 forks. GitHot measured 0 stars in 24 hours. Last checked 2026-11-15 15:50 UTC. Last push 2026-11-15.
What you can do
- rf_discover: Project suite, test, task, tag, file, test metadata (--values), profile (profiles show for a profile's effective settings), and merged robot.toml discovery (robotcode -f json discover|config|profiles), with --search and a compact longname / source:line / tags projection (verbose=true for full items).
- rf_analyze: Millisecond headless LSP semantic static analysis (robotcode -r <root> -f json analyze code).
- rf_doc: Project-aware library, .resource, and keyword documentation (robotcode -f json doc {lib|keywords|keyword}).
- rf_run: Scoped test/task execution (robotcode robot, supporting -bl <longname>, -btm <metadata>, --rpa, -p <profile>, --wrapper, and inline file synchronization for remote test runners).
Measured star growth
- in 24h
- 0
- in 7 days
- Update delayed
- in 15 days
- Update delayed
- in 1 month
- Update delayed
Net star changes over overlapping periods, not daily totals. Missing measurements are left blank. Stars measure attention, not software quality.
About
A Robot Framework MCP Server
ProductivityREADME.md
Originalrf-mcp — Robot Framework Agentic Engineering MCP Server
[!IMPORTANT] rf-mcp is being heavily refactored. Version 2.0 rebuilds it on the RobotCode CLI, and this README already describes that new implementation. See the 2.0 release notes for what changed.
2.0 is not on PyPI yet, so
pip install rf-mcpanduv add rf-mcpstill install 0.36.x. To try 2.0 now, install it from GitHub:uv add --dev "rf-mcp @ git+https://github.com/manykarim/rf-mcp" "robotcode[all]>=2.9.0.dev115"Using rf-mcp 0.36.x or earlier? Install it as a tool and register it with your coding agents:
uv tool install "rf-mcp[all]==0.36.*" robotmcp install # or: claude mcp add rf-mcp -- uvx "rf-mcp[all]==0.36.*"The full 0.36 documentation is at the
v0.36.0tag.
rf-mcp is a lean, customizable Model Context Protocol (MCP) server built on RobotCode (>=2.9.0.dev115) CLI, robotcode session, and FastMCP Skills over MCP (SEP-2640).
It empowers coding agents (Claude Code, OpenAI Codex, Google Antigravity (agy), GitHub Copilot, OpenCode) to discover, analyze, document, author (repl), debug (robot-debug), execute, and maintain Robot Framework tests and tasks across local machines, remote test runners, zero-daemon remote MCP setups, and CI pipelines.
Key Capabilities
8 Focused
robotcode-Powered MCP Tools:rf_discover: Project suite, test, task, tag, file, test metadata (--values), profile (profiles showfor a profile's effective settings), and mergedrobot.tomldiscovery (robotcode -f json discover|config|profiles), with--searchand a compactlongname/source:line/tagsprojection (verbose=truefor full items).rf_analyze: Millisecond headless LSP semantic static analysis (robotcode -r <root> -f json analyze code).rf_doc: Project-aware library,.resource, and keyword documentation (robotcode -f json doc {lib|keywords|keyword}).rf_run: Scoped test/task execution (robotcode robot, supporting-bl <longname>,-btm <metadata>,--rpa,-p <profile>,--wrapper, and inline file synchronization for remote test runners).rf_results: Server-side querying, diffing and merging ofoutput.xml/output.json(robotcode -f json results {summary|show|log|stats|diff}with--search,--sort,--level,--max-depth,--by,--extractscreenshot extraction, andrebot --merge). Result files are chosen only withoutput_path.rf_repl: Stateful multi-turn interactive exploration and test authoring (start,send,wait,status,result,interrupt,restart,list,save,stop) backed byrobotcode -f json session(session start repl,.save -t "Name" file.robot, hot-reload viasession restart, and nativeBrowser.Get Aria Snapshot).rf_debug: Stateful multi-turn live test debugger (start,send,wait,status,result,interrupt,restart,list,stop) backed byrobotcode -f json session(session start debug, pausing on uncaught failures or--break file.robot:line, preservingoutput.xmlvia--output NONE --log NONE --report NONE, and inspecting.where,.vars --user,.list).rf_diagnose: Ranked, library-aware error recovery hinting (Browser, Selenium, Appium, Requests, PlatynUI, BuiltIn, REPL syntax) extensible via<workspace>/.robotframework/hints.toml.
3 Execution Topologies (
server,client, and CI) — Zero Extra Client Daemons:- Mode 1: Full Local (
--mode server,stdioorhttp):rf-mcpruns locally alongside your project and executesrobotcodeandrobotcode sessiondirectly. - Mode 2: Remote Test Runner (
--mode server --transport http):rf-mcpandrobotcoderun on a remote test container/VM (with browsers/devices/displays), accepting inlinefilessynchronization from the coding agent. - Mode 3: Zero-Daemon Remote MCP + Local
robotcode(--mode client --transport http):rf-mcpruns remotely while the coding agent androbotcoderun on the developer's machine.rf-mcpserves project/ecosystem skills over MCP, synthesizes shell-safe localrobotcode&robotcode sessioncommands for PowerShell and Bash, and diagnoses failures viarf_diagnose. The agent'srootis passed torobotcode -rverbatim (it is a path on the client machine); without one,-ris omitted.rf_debug startalso returns a one-shotfallback_commandfor agent shells that kill background processes;rf_replhas none, because a one-shot REPL cannot replay earlier turns.
Client-mode commands are executed by a test in both supported shells: PowerShell 7+ and bash. Windows PowerShell 5.1 is untested (its quoting of native arguments differs). Commands set
PYTHONUTF8=1,PYTHONIOENCODING=utf-8andROBOTCODE_FORCE_AI_AGENT=1.- Mode 1: Full Local (
Skills over MCP (SEP-2640 +
ResourcesAsTools) & Plugin Coexistence:- Serves layered
SKILL.mddirectories over MCP (skill://{name}/SKILL.md+list_resources/read_resourcetools for tool-only agents):- Project-local
<workspace>/.robotframework/skills/ - External plugin directories via
--skills-dir/RF_MCP_SKILLS_DIR(compatible withrobotcodedev/robotframework-agent-pluginsandmanykarim/robotframework-agentskills) - Built-in skills:
rf-robotcode(tool routing, triage, debugging, REPL authoring, results, analysis, configuration; maps the upstream robotcode practices P1-P46),rf-locators(Browser, SeleniumLibrary, AppiumLibrary and PlatynUI locators, shadow DOM and iframes, keyword per intent, library chooser) andrf-requests(RequestsLibrary for REST, SOAP/XML and GraphQL). Detail lives inreferences/files, e.g.skill://rf-robotcode/references/triage.md.
- Project-local
- The server
instructionsare a short intent routing table plus the authoring loop and its finish condition (done only whenrf_analyzeis clean andrf_runpasses).
- Serves layered
OpenTelemetry Observability:
- Built-in child spans (
rf_mcp.discover,rf_mcp.analyze,rf_mcp.doc,rf_mcp.run,rf_mcp.results,rf_mcp.repl,rf_mcp.debug,rf_mcp.diagnose) nested under FastMCP server spans, plus metrics (rf_mcp.commands.total,rf_mcp.command.duration_ms,rf_mcp.hints.generated,rf_mcp.skills.read).
- Built-in child spans (
Installation & Quick Start
rf-mcp needs Python 3.10+ and uv 0.12 or newer (uv self update). It runs
robotcode[all]>=2.9.0.dev115 (currently a pre-release) in your project's own environment, so it sees the libraries
and robot.toml your tests use. Older uv versions (0.9 is confirmed) refuse robotcode's pre-release sub-packages
during the install unless --prerelease=allow is passed.
Option A: one install for all projects (recommended)
uv tool install rf-mcp
rf-mcp init --scope user --agent all --write # registers `rf-mcp` with each installed agent, for every project
Open any Robot Framework project in your agent and the tools work there: rf-mcp finds the project root from the
folder the agent starts it in and runs robotcode with the project's .venv. A project needs only Robot Framework
and its libraries; when its environment has no robotcode (or an older one), rf-mcp adds its own robotcode version
through uv without changing the project. See
Which Python runs your tests.
Option B: install into the project
uv add --dev rf-mcp "robotcode[all]>=2.9.0.dev115"
rf-mcp init --agent all --write # writes .mcp.json, .codex/config.toml, .vscode/mcp.json, ...
The project files init writes start uv run rf-mcp and contain no paths, so they can be committed and work in
every clone. With pip: pip install rf-mcp "robotcode[all]>=2.9.0.dev115". Name robotcode with its pre-release
version as shown: --prerelease=allow or pip --pre would also pull pre-releases of every other dependency (for
example FastMCP alphas).
Check and customize
rf-mcp doctor # which root and environment a project gets, robotcode, skills, hints
rf-mcp init --agent claude --url http://mcp.internal:8000/mcp --write # connect to a remote server instead
rf-mcp sync-skills --agent claude # copy the skills into .claude/skills (or .agents/skills)
init without --write prints what it would change. It replaces only its own rf-mcp entry in existing files;
a file with comments (common in VS Code) is left alone and the entry is printed to paste. With --scope user it
uses each agent's own command (claude mcp add --scope user, codex mcp add, copilot mcp add, code --add-mcp,
agy mcp add, opencode mcp add --global). sync-skills leaves an existing skill folder alone when its content differs (exit code 1, listed
under skipped); pass --force to overwrite it.
Running rf-mcp
# Mode 1: Local stdio MCP server (default); the agent starts it in the project
rf-mcp # optional: -r /path/to/project pins the root, -p ci a profile
# Mode 2: Remote Test Runner over Streamable HTTP
rf-mcp --mode server --transport http --host 0.0.0.0 --port 8000 -r /workspace
# Mode 3: Zero-Daemon Remote MCP Server (synthesizes client-side robotcode commands)
rf-mcp --mode client --transport http --host 0.0.0.0 --port 8000 \
--skills-dir /opt/robotframework-agent-plugins \
--skills-dir /opt/robotframework-agentskills
Docker
The images run Mode 2 with Browser, SeleniumLibrary and RequestsLibrary installed; rf-mcp-vnc adds a display you can watch in the browser. Mount the project at /workspace:
docker run --rm --shm-size=1g -p 8000:8000 -v "$PWD:/workspace" ghcr.io/manykarim/rf-mcp
rf-mcp init --agent claude --url http://localhost:8000/mcp --write
See docs/DOCKER.md for the VNC image and for building with other libraries.
Project Customization (Zero Code Required)
1. Project Skills (<workspace>/.robotframework/skills/)
Create <workspace>/.robotframework/skills/<skill-name>/SKILL.md to teach connected agents your project's custom libraries, page object patterns, and naming rules. rf-mcp automatically discovers and hot-reloads it at skill://<skill-name>/SKILL.md.
2. Custom Error Recovery Hints (<workspace>/.robotframework/hints.toml)
Define project-specific error recovery hints in .robotframework/hints.toml:
[[hints]]
id = "corp-sso-expired"
title = "Corporate SSO token expired"
error_pattern = "401 Unauthorized.*SSO"
keyword_pattern = ".*"
message = "Refresh the session token using the Auth resource before calling the endpoint."
fix_examples = [
"Import Resource resources/auth.resource",
"Refresh SSO Token",
]
relevance = 99
applies_to = ["runtime", "static"] # default; "static" = rf_analyze diagnostics
A file that does not parse, or a rule with an invalid regular expression, is skipped with a warning naming the file, line and rule id; the valid rules and all built-in rules stay active. rf-mcp doctor and the server instructions report the skipped entries.
3. Verified cookbook snippets
Every snippet in the built-in rf-locators shadow DOM / iframe reference and in rf-requests is executed by tests/test_cookbook.py (suites in tests/cookbook/) against local fixtures: a widget page with open, nested and closed shadow roots and same-origin, nested, cross-origin and shadow-hosted iframes (tests/fixtures/web/), and a strict REST/SOAP/GraphQL "ledger" API (tests/fixtures/ledger/). The suites need libraries rf-mcp does not depend on and are skipped unless available:
RF_MCP_COOKBOOK_PYTHON=/path/to/venv-with-requests-browser-selenium/python \
RF_MCP_FIXTURE_PYTHON=/path/to/venv-with-fastapi-uvicorn-strawberry/python \
uv run pytest tests/test_cookbook.py
4. OpenTelemetry Export
Install rf-mcp[otel] and pass --otel-endpoint http://localhost:4318 (or set OTEL_EXPORTER_OTLP_ENDPOINT) to export traces and metrics over OTLP.
Documentation
- Getting started: install, connect an agent, a first session, troubleshooting
- Configuration: options, environment variables, execution modes, skills, hints, OpenTelemetry
- MCP tool reference: every tool and parameter, generated from the published schemas
- Examples: tool sequences for triage, authoring, debugging, reruns, remote runners and client mode
- Docker images: headless and VNC test-runner images
- Release notes 2.0.0: what changed from 0.x, with a tool migration table
- Agent evaluation harness: how rf-mcp is measured with real agents and models
Documentation for rf-mcp 0.36 and earlier is at the v0.36.0 tag.