AgentNexusBLOCK
Continuously verified registry of the APIs, MCP servers and CLIs that AI agents call — live health checks, reliability history, and an anonymous MCP endpoint agents can connect to without a consent screen.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
The continuously verified registry of the APIs, MCP servers and CLIs that AI agents call.
Live: https://agentnexus.app · MCP endpoint (no login): https://agentnexus.app/api/public/mcp
[](https://m8ven.ai/mcp/strategiumfinancepartner-agentnexus-1icap4) [](https://mcpservers.org/servers/strategiumfinancepartner/agentnexus)
Agent Nexus answers one question for an autonomous agent: "what can actually do this, right now, and how exactly do I call it?" Every entry is probed over HTTP on a schedule, so the answer carries a real reliability score instead of a stale README badge.
Listed on the official MCP registry as app.agentnexus/agent-nexus, on Smithery, on Glama and on the M8ven Trust Index.
Connect an agent in one line
MCP (Streamable HTTP, stateless, anonymous — no consent screen, no key):
{
"mcpServers": {
"agent-nexus": {
"type": "http",
"url": "https://agentnexus.app/api/public/mcp"
}
}
}Or over plain HTTP — an agent can register itself and start calling without any human:
# 1. get your own key (instant, free tier: 1000 calls/day)
curl -s -X POST https://agentnexus.app/api/public/keys \
-H 'content-type: application/json' \
-d '{"agent":"my-agent","purpose":"capability discovery"}'
# 2. turn a plain-language need into a callable contract
curl -s 'https://agentnexus.app/api/public/discover?need=send%20transactional%20email' \
-H 'x-api-key: nx_...'MCP tools
9044972b3eb7OBSERVED · 2026-10-11Connect
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 n8n-nodes-agentnexus --env AGENT_NEXUS_API_KEY=${AGENT_NEXUS_API_KEY} --env GITHUB_API_KEY=${GITHUB_API_KEY} --env LOVABLE_API_KEY=${LOVABLE_API_KEY} -- npx -y [email protected]{
"mcpServers": {
"n8n-nodes-agentnexus": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"AGENT_NEXUS_API_KEY": "${AGENT_NEXUS_API_KEY}",
"GITHUB_API_KEY": "${GITHUB_API_KEY}",
"LOVABLE_API_KEY": "${LOVABLE_API_KEY}"
}
}
}
}Exposed tools (11)
9 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
agent-nexus | read | Search and inspect the registry over MCP (Streamable HTTP). |
agent-nexus-authenticated | read | Same tools with OAuth-authenticated access and higher quotas. |
discover | read | Natural-language capability discovery across the registry. |
discover_capabilities | read | Map a plain-language goal (e.g. |
entries.ndjson | read | Full registry dump, one JSON entry per line. |
list_categories | read | Return the fixed taxonomy of Agent Nexus: the three interface layers it indexes ( |
list_entries | write | Enumerate the whole approved catalogue in deterministic slug order, page by page — use this when you want everything (mirroring, auditing, building your own index), not when you are looking for something specific. Read-only and idempotent. Returns {total, page, per_page, pages, results[]}: read |
list_my_submissions | read | List the interfaces the signed-in member submitted, with their moderation status and any reviewer note. |
registry | read | Browse and filter registry entries. |
vote_entry | read | Signal that an approved interface is useful, on behalf of the signed-in member. Calling it again removes the vote. One vote per member per entry. |
x-api-key | write | Optional free agent key, self-issued with POST /api/public/keys. Raises the daily quota from 100 to 1000 calls and unlocks machine submissions. |
Trust audit
BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | FAIL |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (14 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (18)
host === "metadata.google.internal" ||
if (a === 169 && b === 254) return false; // link-local incl. cloud metadata 169.254.169.254
__init__.cpython-313.pyc
__init__.cpython-313.pyc
client.cpython-313.pyc
tools.cpython-313.pyc
endpoint: "http://127.0.0.1:3845/mcp",
('cloudflare-trace-api','Cloudflare Trace','api','See your own egress IP, colo and TLS info.','Diagnostic endpoint returning the requesting IP, datacenter and protocol.','none','https://1.1.1.1/cdn-cgtest_tools.cpython-313-pytest-9.1.1.pyc
.prettierignore
import mcp from "../../../lib/mcp/index";
import mcp from "../../lib/mcp/index";
import mcp from "../../lib/mcp/index";
import mcp from "../../../lib/mcp/index";
import mcp from "../../lib/mcp/index";
@hookform/resolvers, @lovable.dev/cloud-auth-js, @lovable.dev/mcp-js, @lovable.dev/webhooks-js, @paddle/paddle-node-sdk, @radix-ui/react-accordion, @radix-ui/react-alert-dialog, @radix-ui/react-aspect
n8n-workflow, typescript
- Self-service API key: `POST https://agentnexus.app/api/public/keys`
Gates applied: no_behavioural_pass.
9044972b3eb7full audit observations/trust-audit/mcp-server/strategiumfinancepartner__agentnexus.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 9044972b3eb7 | BLOCK | D | 69 | first audit |
Questions
What is the AgentNexus MCP server?
Continuously verified registry of the APIs, MCP servers and CLIs that AI agents call — live health checks, reliability history, and an anonymous MCP endpoint agents can connect to without a consent screen.
What tools does AgentNexus expose?
11 in total: 9 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is AgentNexus safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (69/100) and found 2 critical or high issues in the source. Each one is listed on this page with the file and line it is on.
What credentials does AgentNexus need?
It reads AGENT_NEXUS_API_KEY, GITHUB_API_KEY and LOVABLE_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 AgentNexus run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on npm as n8n-nodes-agentnexus at 0.1.7.
How current is this page?
The grade is for one exact copy of the source (9044972b3eb7), read on 2026-10-11. The repository is watched and re-audited when it changes.