# @savantoai/mcp-server

Savanto AI MCP (Model Context Protocol) server — lets Claude, Cursor, and other agents provision and configure Savanto workspaces.

- **Type:** MCP server
- **Trust:** 85/100 (A), scored on the package rubric
- **Verification:** verified (build provenance)
- **Version:** 0.2.1
- **Author:** Savanto
- **License:** MIT
- **npm:** @savantoai/mcp-server
- **Endpoints:** streamable-http https://mcp.savanto.ai/mcp
- **Source:** https://github.com/SavantoAI/mcp-server
- **Endpoint health:** reachable (last checked 2026-08-26T10:53:28.185Z, 1 sample) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

85/100 (A), scored on the package rubric
- Publisher verified: no
- Build provenance: verified attestation
- npm trusted publishing (OIDC): yes
- Install scripts: nothing suspicious found
- Prompt-injection scan: not run
- Obfuscation scan: not run
- Evidence age: 19 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-08-09T16:51:12.853Z
- **Version scanned:** 0.2.1
- **CVEs:** none found by OSV at scan time

## Tools

40 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `get_search_analytics`
- `get_chat_analytics`
- `get_feedback_analytics`
- `list_feedback`
- `search_search_logs`
- `chat`
- `update_workspace_settings`
- `list_custom_domains`
- `create_custom_domain`
- `update_custom_domain`
- `delete_custom_domain`
- `get_chat_widget_config`
- `update_chat_widget_config`
- `get_search_widget_config`
- `update_search_widget_config`
- `upsert_product`
- `bulk_upsert_products`
- `list_products`
- `get_product`
- `patch_product`
- `delete_product`
- `bulk_delete_products`
- `search_products`
- `upsert_post`
- `bulk_upsert_posts`
- `get_post`
- `patch_post`
- `delete_post`
- `bulk_delete_posts`
- `search_posts`
- `start_crawl`
- `get_crawl_status`
- `get_crawl_history`
- `get_crawl_config`
- `update_crawl_config`
- `whoami`
- `get_tenant_usage`
- `upsert_prompt`
- `bulk_upsert_prompts`
- `list_prompts`

## Install

**Verdict: install** — No blocking findings and no open coverage gaps — safe to install as configured.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"mcp-server\": {\n      \"command\": \"npx\",\n      \"args\": [\n        \"-y\",\n        \"@savantoai/mcp-server\"\n      ]\n    }\n  }\n}"
```

## Blast radius

Extensive to critical — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: deletes data; runs locally and hosted.
- Floor 46, ceiling 70 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/%40savantoai%2Fmcp-server
- Install plan: https://forgeregistry.com/api/v1/packages/%40savantoai%2Fmcp-server/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/%40savantoai%2Fmcp-server
- HTML page: https://forgeregistry.com/registry/%40savantoai%2Fmcp-server
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.