Agents MCP server
io.github.absolutejs/agents·v0.2.0Search verified agents and production agent-first AbsoluteJS packages.
0 stars95 downloads/wk
Reviews
Write oneNobody has reviewed Agents yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agents tools (5)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
get_agentGet one verified agent listing by its canonical discovery ID or agent URL.
get_packageGet one AbsoluteJS package by its exact scoped npm name.
registry_statusReport the public registry endpoint, generation time, schema, and agent count.
search_agentsSearch cryptographically verified agent listings by text, capability, or interface protocol.
search_packagesSearch production AbsoluteJS packages by purpose, category, or supported agent standard.
Public scan report
scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it
- Code scan15 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 15 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Agents compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 92/100
- higher than 90% of 4,460 AI and agents servers
- Tools
- 5
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 95
- more than 63% of 1,538 AI and agents servers with a package
What its tools let an agent do: 5 read
Install Agents in Claude Code, Cursor or VS Code
Runs npx -y @absolutejs/agents-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add agents -- npx -y @absolutejs/agents-mcp
What the publisher says
From the Agents repository's README, as published. We do not edit it. Read it on GitHub
@absolutejs/agents-mcp
A production, read-only MCP server for finding cryptographically verified AI agents and production agent-first packages in the AbsoluteJS public registry. It gives MCP clients one installable discovery surface for agent names, capabilities, protocols, publishers, authentication metadata, and signed descriptors.
Run it
{
"mcpServers": {
"absolute-agents": {
"command": "npx",
"args": ["-y", "@absolutejs/agents-mcp"]
}
}
}No credentials are required. The server fetches the public HTTPS registry, refuses redirects, bounds response size and time, validates every record, and caches successful indexes briefly. To use a compatible federated registry, set ABSOLUTEAGENTREGISTRYURL to its HTTPS index URL. The package catalog is independently configurable with ABSOLUTEPACKAGEREGISTRYURL.
MCP surface
Arazzo/WebMCP/HTTP/OpenAPI/WebSocket interface type, with bounded pagination.
- search_agents filters verified listings by text, capability, and MCP/A2A/
category, and supported standard.
- get_agent returns one listing by canonical discovery ID or agent URL.
- search_packages filters the production AbsoluteJS catalog by purpose,
- get_package returns one package by exact scoped npm name.
- registry_status reports freshness, schema, endpoint, and verified count.
- absolute-agents://registry/index exposes the validated index as a resource.
- absolute-agents://packages/index exposes the validated package catalog.
All tools are marked read-only. Discovery never grants authorization: callers must follow each returned agent's advertised OAuth, approval, and delegation requirements before taking actions.
Library use
import { AgentRegistryClient, createAgentsMcpServer } from "@absolutejs/agents-mcp";
const registry = new AgentRegistryClient();
const results = await registry.search({ capability: "calendar", interfaceType: "a2a" });
const { server } = createAgentsMcpServer({ client: registry });The npm package declares mcpName: io.github.absolutejs/agents and ships the official MCP Registry server.json metadata alongside its AbsoluteJS manifest.
Nothing above is checked by us. What we check is on the safety report.
Agents: common questions
- Is Agents MCP server safe?
- Yes, by our scan: it is graded A (92/100). Read the Agents safety report
- How do I install Agents?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agents need an API key?
- No secret keys are declared. It reads 2 settings from the environment.
- Is Agents maintained?
- The last commit was 55 days ago (2026-09-10). The latest release is v0.2.0.
- What can I use instead of Agents?
- Servers from other publishers that do the same job: Basic Memory MCP server, HOL Guard MCP server and Agent-Native Chat MCP server.
- How does Agents compare with other AI and agents MCP servers?
- safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 5 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Agents
Same job from other publishers: the closest match first, then the best rated.
- Basic MemoryLocal-first knowledge management with bi-directional LLM sync via Markdown files.not reviewedWidely usedB
- HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.not reviewedEstablishedA
- Agent-Native ChatMinimal chat-first app with durable threads, actions, and the app-agent loopnot reviewedEstablishedA
- Agent RecallCorrection-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.not reviewedEstablishedA
- Agent Security ScannerSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.not reviewedEstablishedC