RagieSAFE
Ragie Model Context Protocol Server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
This project is no longer needed. Ragie now supports MCP natively as a streamable HTTP server. See docs here: [https://docs.ragie.ai/docs/mcp-overview]
If you would like users within your company to be able to access you knowledge base in applications like Claude or ChatGPT, you may need MCP Bridge
Ragie Model Context Protocol Server
A Model Context Protocol (MCP) server that provides access to Ragie's knowledge base retrieval capabilities.
Description
This server implements the Model Context Protocol to enable AI models to retrieve information from a Ragie knowledge base. It provides a single tool called "retrieve" that allows querying the knowledge base for relevant information.
Prerequisites
- Node.js >= 18
- A Ragie API key
Installation
The server requires the following environment variable:
RAGIE_API_KEY(required): Your Ragie API authentication key
The server will start and listen on stdio for MCP protocol messages.
Install and run the server with npx:
RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server
Command Line Options
The server supports the following command line options:
--description, -d: Override the default tool description with custom text--partition, -p: Specify the Ragie partition ID to query
Examples:
# With custom description RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company knowledge base for information" # With partition specified RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --partition your_partition_id # Using both options RAGIE_API_KEY=your_api_key npx @ragieai/mcp-server --description "Search the company knowledge base" --partition your_partition_id
Cursor Configuration
To use this MCP server with Cursor:
Option 1: Create an MCP configuration file
- Save a file c
017c2ab326e7OBSERVED · 2026-10-07Connect
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. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add mcp-server --env RAGIE_API_KEY=${RAGIE_API_KEY} -- npx -y @ragieai/[email protected]{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@ragieai/[email protected]"
],
"env": {
"RAGIE_API_KEY": "${RAGIE_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
retrieve | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, commander, ragie, zod, @types/node, tsx, typescript
Gates applied: no_behavioural_pass.
017c2ab326e7full audit observations/trust-audit/mcp-server/ragieai__ragie.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 |
|---|---|---|---|---|---|
| 2026-10-07 | 017c2ab326e7 | SAFE | B | 89 | first audit |
Questions
What is the Ragie MCP server?
Ragie Model Context Protocol Server
What tools does Ragie expose?
1 in total: 1 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Ragie safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Ragie need?
It reads RAGIE_API_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Ragie run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @ragieai/mcp-server at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (017c2ab326e7), read on 2026-10-07. The repository is watched and re-audited when it changes.