ClaudeRBLOCK
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
ClaudeR - The Modern Researcher's Toolkit
Connect a live R or Python session, in RStudio or Positron, to Claude Code, Codex, or any MCP-based LLM agent. For interactive analysis, multi-agent orchestration, and automated manuscript auditing.
ClaudeR connects MCP-configured LLM agents, like Claude Code or Codex, to the R session you are already working in. The agent runs code where your cleaned data and fitted models actually are, sees the plots it draws, reads the objects in your environment, and can edit the file open in your editor. A companion Python package does the same for a li
da2fa18eb721OBSERVED · 2026-10-03Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add clauder-mcp -- None clauder-mcp==0.16.1
Exposed tools (16)
12 read · 4 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
cancel_annotation_job | read | Cancel a running annotation job. The current row finishes before stopping. Already-saved rows are kept and the job is resumable. |
clean_error_log | read | Clean a ClaudeR session log by removing error blocks and their duplicates. Parses the log, finds errors, checks if a fix follows each error, removes the error blocks and any duplicate code blocks that preceded them. Returns a report of what was found and removed. |
connect_session | read | Connect to a specific RStudio session by name. Use list_sessions first to see available sessions. Subsequent tool calls will be routed to this session. |
create_task_list | write | Create a task list for the current analysis |
execute_r | write | Execute R code and return the output |
execute_r_with_plot | write | Execute R code that generates a plot |
get_annotation_job_status | read | Check the status of a running or completed annotation job started with run_annotation_job. |
get_async_result | read | Check the result of an async R job. Waits ~10 seconds before checking to avoid excessive polling. If the job is still running, call this again. |
get_r_info | read | Get a summary of the R environment. Returns package count (not full list), first 20 variables, and R version. Use requireNamespace( |
get_session_history | read | Get execution history for the current R session. Can filter by agent to see what a specific agent has done. |
get_viewer_content | read | Get HTML content from the RStudio Viewer pane (HTML widgets like plotly, DT, leaflet). Returns paginated chunks. Call with offset to get more. |
list_checkpoints | read | List saved R session checkpoints (file, time, size MB) for the current session, newest last. |
list_sessions | read | List available RStudio sessions that this agent can connect to. Shows session name, port, and PID for each active session. |
read_file | read | Read the contents of a file from disk. Handles plain text (R scripts, logs, CSVs) and manuscripts: .docx and .pdf are transparently extracted as structured text with headings prefixed by #s and table cells emitted row-wise as |
search_project_code | read | Search for a regex pattern across project source files (.R, .Rmd, .qmd). Returns matching file, line number, and code snippet. Uses base R grep — safe to use even with system() blocked. |
update_task_status | write | Update the status of a task and optionally add notes |
Trust audit
BLOCKgrade D · trust 62/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (2 observation(s))
- Network
- declared (11 observation(s))
- Shell
- declared (3 observation(s))
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (14)
.clauder_result <- withVisible(eval(parse(text = code), envir = work_env))
withVisible(eval(parse(text = code), envir = env)),
exec(compile(code, "<clauder>", "exec"), STATE.namespace)
sprintf("Running on http://127.0.0.1:%d", input$port)sprintf("Running on http://127.0.0.1:%d", input$port)return f"http://127.0.0.1:{pick['port']}"print("clauder: listening on http://127.0.0.1:%d as session '%s'%s.\n".Rbuildignore
is.symbol(expr[[2]]) && as.character(expr[[2]]) %in% funcs) eval(expr, env)
r = urllib.request.Request("http://127.0.0.1:%d" % PORT,self.assertTrue(base64.b64decode(r["plot"]["data"]).startswith(b"\x89PNG"))
No filter fixes this, because running code is the feature. Mitigate by treating agent sessions over third-party documents as you would running a stranger's script: do it in a project directory, keep l
- **MCP Server Failed to Start**: If using `uvx`, ensure `uv` is installed (`curl -LsSf https://astral.sh/uv/install.sh | sh`). If using the legacy method, this usually means the wrong Python environm
- **Deep-dive audit release (R 0.3.1 / clauder-mcp 0.6.2).** 20+ bug fixes across the addin, bridge, and Lab Mode: reopened addin UIs now share live state with the running server (settings toggles wor
Gates applied: no_behavioural_pass.
da2fa18eb721full audit observations/trust-audit/mcp-server/imnmv__clauder.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-03 | da2fa18eb721 | BLOCK | D | 62 | first audit |
Questions
What is the ClaudeR MCP server?
Connect RStudio to Claude Code, Codex, Gemini, and other LLM agents via MCP. Multi-agent orchestration, automated manuscript auditing, and zero-config setup with uvx
What tools does ClaudeR expose?
16 in total: 12 read-only, 4 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is ClaudeR safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (62/100) and found 3 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does ClaudeR need?
No credential environment variables were found in its source, so it appears to need none.
How does ClaudeR run?
It speaks stdio, so it runs as a local process your client starts. It is published on PyPI as clauder.
How current is this page?
The grade is for one exact copy of the source (da2fa18eb721), read on 2026-10-03. The repository is watched and re-audited when it changes.