vetagentBLOCK
VetAgent — token risk intelligence MCP for AI agents. Cloudflare Worker deployment. Assess token risk (liquidity/honeypot/rug) and return actionable low/medium/high verdict. Remote MCP at https://vetagent.dev/mcp.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://smithery.ai/servers/jake-gu95/vetagent) [](https://registry.modelcontextprotocol.io/) [](https://glama.ai/mcp/connectors/dev.vetagent/vetagent) [](LICENSE)
A pre-trade safety check for AI agents. Before an agent buys, holds, or recommends a token, it calls VetAgent and gets an actionable verdict — low / medium / high / unknown — plus the specific signals behind it, instead of a wall of numbers to interpret.
Remote MCP endpoint: `https://vetagent.dev/mcp` · Landing page: https://vetagent.dev Using it, or think it got a token wrong? [email protected] — or open an issue.
// assess_token_risk("0x...", chain_hint="ethereum")
{
"risk_level": "medium",
"risk_score": 36,
"confidence": "high",
"signals": [
{"severity": "ok", "name": "Liquidity is adequate", "category": "liquidity"},
{"severity": "ok", "name": "Buys and sells normally", "category": "honeypot"},
{"severity": "warn", "name": "Contract is closed source", "category": "contract"}
],
"recommendation": "Medium risk. Real signals fired but none are fatal. Review liquidity, holder distribution and contract permissions before deciding."
}Install
Nothing to install. It is a remote server: no package, no container, no API key, no signup. Add one URL.
Claude Code:
claude mcp add --transport http vetagent https://vetagent.dev/mcp
Cline, Cursor, Claude Desktop, or any other MCP client — add to the MCP config:
{
"mcpServers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}Confir
0811353ba419OBSERVED · 2026-10-12Connect
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 vetagent --env CLOUDFLARE_API_TOKEN=${CLOUDFLARE_API_TOKEN} --env QUICKINTEL_API_KEY=${QUICKINTEL_API_KEY} -- uvx vetagent{
"mcpServers": {
"vetagent": {
"command": "uvx",
"args": [
"vetagent"
],
"env": {
"CLOUDFLARE_API_TOKEN": "${CLOUDFLARE_API_TOKEN}",
"QUICKINTEL_API_KEY": "${QUICKINTEL_API_KEY}"
}
}
}
}Exposed tools (1)
1 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
budgeted-review | read | Multi-dimension adversarial review with a hard agent ceiling |
Trust audit
BLOCKgrade D · trust 61/100 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 | PASS |
| 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
- none-observed
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- found
Findings (25)
{"seen_at": "2026-10-12T09:18:01.737143+00:00", "chain": "eth", "kind": "new", "pool_id": "eth_0x9eb16fe4cf77c070b50e71e3c6a0b079f93b65c7", "pool_address": "0x9eb16fe4cf77c070b50e71e3c6a0b079f93b65c7"{"seen_at": "2026-10-10T18:39:59.505402+00:00", "chain": "eth", "token": "0xdd3e50a042454e27892823af11f93139cd11ab07", "pool_address": "0xedde0201ced153bcf8af946bc73ddcb6a09ca68d", "pool_created_at":{"seen_at": "2026-10-11T08:58:19.060488+00:00", "chain": "eth", "token": "0xb4782511bece17a113b73917a5a0aeea15028b07", "pool_address": "0x7cbe1328684b5e4618d2dd3e435610f27d6d9ec0", "pool_created_at":{"seen_at": "2026-10-11T08:58:19.060488+00:00", "chain": "eth", "token": "0x3581232fb8e898e66bdaa6efcdc1edf7ee324b07", "pool_address": "0x896a79c35a17583e7b9137dae8056cb813b5c4d7", "pool_created_at":{"seen_at": "2026-10-11T08:58:19.060488+00:00", "chain": "eth", "token": "0xad0b005a2e247b9ef8a45df403e627c37174db07", "pool_address": "0xb543a55bf66b962a5433e72195667e87c4899e94", "pool_created_at":{"chain": "base", "address": "0x00000e7efa313f4e11bfff432471ed9423ac6b30", "code": "0x608060405234801561000f575f5ffd5b5060043610610135575f3560e01c806379cc6790116100b6578063a9059cbb1161007a578063a9059c{"chain": "base", "address": "0x001aad84c21a5cd4d696c56d44866e9703c43f77", "code": "0x608060405234801561000f575f80fd5b5060043610610213575f3560e01c80637f2eecc31161011f578063c630948d116100a9578063d91694{"chain": "base", "address": "0x00e57ec29ef2ba7df07ad10573011647b2366f6d", "code": "0x6080604052600436106101d15760003560e01c806395d89b41116100f7578063cb96372811610095578063e2f4560511610064578063e2f456{"chain": "base", "address": "0x00f3c42833c3170159af4e92dbb451fb3f708917", "code": "0x60806040526004361061017b575f3560e01c8063880cdc31116100cd578063a9059cbb11610087578063d559f05b11610062578063d559f05b{"chain": "base", "address": "0x010e74bc5f0020cd313a21b87f30997213cb1bb1", "code": "0x6080604052600436106100f2575f3560e01c80638119c06511610087578063a9059cbb11610057578063a9059cbb14610297578063dd62ed3etoken = "0x1111111111111111111111111111111111111111"
TOKEN = '0x1111111111111111111111111111111111111111'
TOKEN = "0x5555555555555555555555555555555555555555"
TOKEN = "0x226a2fa2556c48245e57cd1cba4c6c9e67077dd2"
secret = "fixture-secret-must-not-escape"
h = hashlib.md5((address or "").encode("utf-8")).hexdigest()return "0x" + hashlib.sha1(symbol.encode("utf-8")).hexdigest()raw = bytes.fromhex(h[128:128 + n * 2])
raw = bytes.fromhex(h).rstrip(b"\x00")
PNG = base64.b64decode(
f.write("PNG = base64.b64decode(\n")| E30 | The upstream contract test **derives** its field list from `src/risk.py` rather than carrying one, and asserts a **measured distribution** per path, not presence. Its CI job is no longer `cont
the server issues no Mcp-Session-Id, so each POST is its own context and
bench/rugcheck_scores_rerun.jsonl
bench/snapshots/pools-2026-09-05.ndjson
Gates applied: no_behavioural_pass.
0811353ba419full audit observations/trust-audit/mcp-server/jakegu1__vetagent.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 |
|---|---|---|---|---|---|
| 2026-10-12 | 0811353ba419 | BLOCK | D | 61 | first audit |
Questions
What is the vetagent MCP server?
VetAgent — token risk intelligence MCP for AI agents. Cloudflare Worker deployment. Assess token risk (liquidity/honeypot/rug) and return actionable low/medium/high verdict. Remote MCP at https://vetagent.dev/mcp.
What tools does vetagent 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 vetagent safe to connect to an agent?
No — not without reading the findings first. The audit graded it D (61/100) and found 5 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 vetagent need?
It reads CLOUDFLARE_API_TOKEN and QUICKINTEL_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 vetagent run?
It speaks streamable-http, so it runs as a service you connect to over the network. It is published on PyPI as vetagent.
How current is this page?
The grade is for one exact copy of the source (0811353ba419), read on 2026-10-12. The repository is watched and re-audited when it changes.