Skip to main content

Ragento

Ragento MCP

Analytics inside Cursor, Claude Code, Windsurf, and Antigravity.
Purpose-built MCP tools for ingest, catalog, SQL, NL query, profiling, and deep analysis.

Install guide · Why Ragento MCP · Platform


Quick install

curl -fsSL https://ragento.ai/install/mcp.sh | bash

Then enable Ragento in your IDE's MCP settings. Sign-in opens automatically in the browser (app.ragento.ai) and is saved locally.

Manual config

Add to ~/.cursor/mcp.json (or your IDE's MCP config):

{
  "mcpServers": {
    "ragento": {
      "command": "uvx",
      "args": ["ragento-mcp@latest"],
      "env": {
        "RAGENTO_API_URL": "https://backend.ragento.ai/api/v1",
        "RAGENTO_APP_URL": "https://app.ragento.ai"
      }
    }
  }
}
IDE Config path
Cursor ~/.cursor/mcp.json
Claude Code ~/.claude.json or project .mcp.json
Windsurf ~/.codeium/windsurf/mcp_config.json
Antigravity ~/.gemini/antigravity/mcp_config.json

How auth works

  1. Enable the MCP server in your IDE (stdio process starts).
  2. If not signed in, your browser opens app.ragento.ai for OAuth.
  3. Approve access once — tokens save to ~/.config/ragento-mcp/credentials.json (auto-refresh, ~90 days).
  4. Ask your agent to list sources, ingest, or query — no manual ragento_connect step.

Use ragento_disconnect only to switch accounts or sign out.

Tools

Tool Purpose
ragento_list_sources List your data sources
ragento_get_catalog User-scoped tables, columns, SQL hints
ragento_ingest CSV, databases, API captures, text docs
ragento_wait_for_source Poll until ingestion / profiling completes
ragento_run_sql Execute SQL on your sources
ragento_query Natural-language answers (NL2SQL)
ragento_fetch_data NL or SQL → table/chart artifacts
ragento_analyze Deep multi-step investigation
ragento_get_profile Sentinel column classifications
ragento_business_context MDL, graphs, memory, documents
ragento_interview_context Guided KPI / metric capture
ragento_get_insights Insight feed and discovery
ragento_connect Optional manual re-login
ragento_disconnect Sign out on this machine

Environment

Variable Default Description
RAGENTO_API_URL https://backend.ragento.ai/api/v1 API gateway
RAGENTO_APP_URL https://app.ragento.ai OAuth login
RAGENTO_MCP_AUTO_AUTH 1 Set 0 to disable automatic browser sign-in
RAGENTO_MCP_TOKEN — Legacy static token (skips OAuth)

CLI helpers

uvx ragento-mcp@latest install-cursor   # write ~/.cursor/mcp.json
uvx ragento-mcp@latest                  # run stdio MCP server

License

MIT — see LICENSE.

Metadata

Release files for ragento-mcp 0.2.4

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ragento-mcp 0.2.4
File Size Uploaded Provenance Actions
ragento_mcp-0.2.4.tar.gz 26.9 kB Without provenance Details for ragento_mcp-0.2.4.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for ragento-mcp 0.2.4
File Interpreter ABI Platform Actions
ragento_mcp-0.2.4-py3-none-any.whl Python 3 none any Details for ragento_mcp-0.2.4-py3-none-any.whl

Total release size: 50.2 kB

Release files / ragento_mcp-0.2.4.tar.gz

Download URL ragento_mcp-0.2.4.tar.gz
Size 26.9 kB
Tags Source
SHA-256 checksum
How to use checksums
b908b09c252cce5eea274ffd08151160f978e9f25382a5d4ab442352caca1dec
BLAKE2b-256 checksum
How to use checksums
0fd2f98330631510fc3fc0fbc1ce0cdd77d736df9a33f367657dbc52d09a09e2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.8.6

Release files / ragento_mcp-0.2.4-py3-none-any.whl

Download URL ragento_mcp-0.2.4-py3-none-any.whl
Size 23.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
511a859aea6876659a6e6f5b0d814ac9c7bbdad57aada951fb5e874bab024ed3
BLAKE2b-256 checksum
How to use checksums
f018f58fff24d2d770a614593eefb56a1a1434e11140f28d5639ac9777888952
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.8.6

Security for ragento-mcp 0.2.4

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.2.4 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page