This server provides tools for reproducible Stata execution with project-local management, strong provenance, immutability, and approval controls.
Project management: project_init initializes a project with a human-readable artifact directory; project_status inspects project, Stata, backend, and capabilities.
Analysis planning: plan_prepare creates/updates a privacy-safe draft plan; plan_approve freezes and cryptographically locks a plan with explicit approval evidence (approver, SHA-256 hash).
Run lifecycle: run_prepare creates an immutable, descriptively named run; run_execute runs it synchronously or in background with optional timeout; run_status reads lifecycle state; run_control cancels active background runs.
Data & artifacts: data_inspect shows dataset metadata, missingness, labels, and previews; artifact_read reads bounded text or image artifacts; results_get returns typed structured results; graph_get lists or reads verified graph payloads.
Stata help: stata_help retrieves command documentation from the local installation.
Deprecated legacy tools (scheduled for removal at v0.3.0): stata_do, get_data_info, help, read_log, write_dofile, append_dofile, read_file, load_figure, mk_dir — all replaced by the above tools.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@STATA-MCP Repro Run my approved plan for the cohort analysis and show the key results."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Project-local, reproducible Stata execution for humans and AI agents. Every managed analysis stays beside its source project and produces immutable, readable do-files, logs, results, graphs, and provenance.
Existing Stata MCP servers prove that agents can call Stata. STATA-MCP Repro adds the controls required for real research: explicit project ownership, deterministic planning gates, immutable run identity, process-tree cancellation, typed results, graph provenance, safe migration, and one shared human/agent ledger.
Core guarantees:
startup never creates a workspace;
no forced stata-mcp-folder and no copied central archive;
one .stata-mcp.toml selects a human-readable project-relative artifact directory;
run names are descriptive and collision-safe;
completed runs are immutable and every artifact is SHA-256 bound to its run;
medical and other material analyses require a reviewed, approved plan;
dashboard listens only on 127.0.0.1 with an expiring bearer token;
humans and agents create the same canonical run records.
Related MCP server: AI Workbench MCP
Prerequisites: Python 3.11–3.13, a separately licensed Stata installation, and uv.
git clone https://github.com/taewat07/STATA-MCP-AGENT.git
cd STATA-MCP-AGENT
uv tool install .
stata-mcp install --all
cd "/path/to/research-project"
stata-mcp project init --artifact-dir "analysis/stata" --name "Readable study name"
stata-mcp doctorRestart the AI client after installation. Use stata-planner to inspect and approve a material analysis, then stata-analyst to execute it. Humans can inspect the same ledger with:
stata-mcp dashboard --project .The command prints the loopback URL and a short-lived token. The VS Code client connects to this service; it never starts or stops the MCP server.
Read the installation guide, architecture, human and agent workflows, provenance contract, and security model. Legacy users should follow the copy-first migration guide.
Contributions follow CONTRIBUTING.md, the Code of Conduct, and the public security policy.
Pre-release 0.1.x; APIs may change under the documented two-release deprecation policy. Derived from SepineTam's MCP-for-Stata 1.21.3; see THIRD_PARTY_NOTICES.md. Not affiliated with or endorsed by StataCorp LLC. Licensed AGPL-3.0-or-later.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Cross-agent artifact workspace with provenance across Claude Code, Codex, Cursor, LangGraph.
Durable agent-to-agent handoffs and shared scratchpad for multi-agent workflows.
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/taewat07/STATA-MCP-AGENT'
If you have feedback or need assistance with the MCP directory API, please join our Discord server