AgentsetSAFE
Agentset MCP Server - Build RAG with Agentic superpowers
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
MCP server for Agentset, an open-source platform for Retrieval-Augmented Generation (RAG). Designed for developers who want to build intelligent, document-based applications quickly and efficiently.
[![npm version][npm-badge]][npm] [![License][license-badge]][license] [![Build Status][build-badge]][build] [![Downloads][downloads-badge]][npm] [![Size][size-badge]][npm]
Installation
using npm:
AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id
using yarn:
AGENTSET_API_KEY=your-api-key yarn dlx @agentset/mcp --ns your-namespace-id
using pnpm:
AGENTSET_API_KEY=your-api-key pnpm dlx @agentset/mcp --ns your-namespace-id
Adding to Claude
{
"mcpServers": {
"agentset": {
"command": "npx",
"args": ["-y", "@agentset/mcp@latest"],
"env": {
"AGENTSET_API_KEY": "agentset_xxx",
"AGENTSET_NAMESPACE_ID": "ns_xxx"
}
}
}
}Tips
Passing namespace id as an environment variable
AGENTSET_API_KEY=your-api-key AGENTSET_NAMESPACE_ID=your-namespace-id npx @agentset/mcp
Passing a custom tool description
AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id -d "Your custom tool description"
Passing a tenant id:
AGENTSET_API_KEY=your-api-key npx @agentset/mcp --ns your-namespace-id -t your-tenant-id
API Reference
Visit the full documentation for more details.
[docs]: https://docs.agentset.ai/ [build-badge]: https://github.com/agentset-ai/mcp-server/actions/workflows/release.yml/badge.svg [build]: https://github.com/agentset-ai/mcp-server/actions/workflows/release.yml [license-badge]: https://badgen.net/github/license/agentset-ai/mcp-server [license]: https://github.com/agentset-ai/mcp-server/blob/main/LICENSE [npm]: https://www.npmjs.com/package/@agentset/mcp [npm-badge]: https://badgen.net/npm/v/@agentset/mcp [downloads-badge]: https://img.shield
69bd75dc8901OBSERVED · 2026-10-08Connect
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 --env AGENTSET_API_KEY=${AGENTSET_API_KEY} -- npx -y @agentset/[email protected]{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@agentset/[email protected]"
],
"env": {
"AGENTSET_API_KEY": "${AGENTSET_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
knowledge-base-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, agentset, commander, node-fetch, zod, @changesets/cli, @eslint/compat, @ianvs/prettier-plugin-sort-imports
Gates applied: no_behavioural_pass.
69bd75dc8901full audit observations/trust-audit/mcp-server/agentset-ai__agentset.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 |
|---|---|---|---|---|---|
| 2026-10-08 | 69bd75dc8901 | SAFE | B | 89 | first audit |
Questions
What is the Agentset MCP server?
Agentset MCP Server - Build RAG with Agentic superpowers
What tools does Agentset 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 Agentset 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 Agentset need?
It reads AGENTSET_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 Agentset run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @agentset/mcp at 1.3.0.
How current is this page?
The grade is for one exact copy of the source (69bd75dc8901), read on 2026-10-08. The repository is watched and re-audited when it changes.