
VetAgent — token risk intelligence MCP for AI agents. Cloudflare Worker deployment. Assess token
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.
·
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."
}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/mcpCline, Cursor, Claude Desktop, or any other MCP client — add to the MCP config:
{
"mcpServers": {
"vetagent": {
"type": "http",
"url": "https://vetagent.dev/mcp"
}
}
}Confirm it worked — three tools should come back:
curl -s -X POST https://vetagent.dev/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Not using MCP? The same engine answers over plain HTTP:
GET https://vetagent.dev/assess/<address>
See llms-install.md for the version written for an agent doing the
installing, and docs/AGENT-INTEGRATION.md for how to use
the output once connected.
unknown is not lowThis is the single most important thing to know about the output.
VetAgent is fail-closed. When a check cannot run — an upstream is down, a
buy/sell simulation fails, no liquidity data comes back — it returns unknown and
lists exactly what was missing in evidence.data_gaps. It never substitutes an
optimistic middle value, and it never sizes a position for you.
confidence measures how complete the input data was, not how safe the token is.
A risk tool that honestly says "I don't know" is useful. One that guesses is not.
| Tool | What it does |
|---|---|
assess_token_risk(address, chain_hint?, verbose?) | Full risk profile: liquidity depth, pair age and same-ticker impersonation on all eight chains; sellability simulation, taxes, contract permissions and upstream aggregate verdicts on Ethereum, BSC and Base; mint/freeze authority and Token-2022 extensions on Solana. On Solana, holder concentration is reported only when RugCheck supplies a holder list; missing lists remain a coverage gap. |
get_token_liquidity(address, chain_hint?) | Liquidity snapshot for the primary pair, with an explicit status so "upstream failed" is distinguishable from "no pools exist" |
find_new_hot_pools(chain?, limit?, listing?) | Default mixed scans new then trending. For active pools use listing=trending; inspect age, current liquidity and volume. These do not establish sustained funding, exit availability or safety. Discovery only — not a safety endorsement |
Pass chain_hint whenever you know it. Ethereum forks such as PulseChain inherit
contract addresses, so the same address exists on multiple chains with wildly
different prices; the hint removes that ambiguity. (Without it, VetAgent prefers
canonical chains — see _CHAIN_RANK in src/risk.py.)
Full agent-facing contract: docs/AGENT-INTEGRATION.md.
Most token-risk tools publish a feature list. We publish our error rates and the method behind them — including the parts that do not work yet — against labels produced by data sources the engine does not read.
What is measured today: a 1.9% false positive rate on 162 healthy tokens, a 13.0% false-block rate (20 of 154 liquid healthy tokens rated medium or high, which an agent will also refuse), a 20.7% unknown rate, and 21.2% of GoPlus-tagged centralised tokens rated high -- almost all abandoned pools holding cents, not USDT, which is rated low.
What is not measured yet: recall you could rely on. Sampling has turned up 30 dead tokens in 576,
because every public source ranks by liquidity and rugged pools fall off the listing
entirely, and the adversarial cohort is 17 contracts. Recall on those two small cohorts is
published in bench/results.md beside a contract-signals-only column, because most of
what they catch is an empty pool rather than a hostile contract. A population-level
detection rate waits until the daily snapshot archive matures enough to supply a real cohort. An earlier version of this section claimed "measured recall",
which the benchmark file itself contradicted.
→ bench/results.md — current numbers, method, and known limits.
Why it is built this way:
unknown rate reported alongside recall. A tool that answers unknown to
everything has perfect recall and zero value.The benchmark uses the pinned logical clock 2026-09-21T02:00:00Z. Use an isolated working copy and a matching local cache for reproduction:
python bench/run_benchmark.py --replayReplay makes no network requests. A missing answer returns exit 4, lists missing URLs, and leaves existing result files unchanged. A complete replay can write bench/results.json and bench/results.md. The cache is not tracked or published with this repository; a fresh clone is not guaranteed to reproduce the published figures.
Plain run mode can fetch missing answers and write dated cache entries. An intentional
refresh uses python bench/run_benchmark.py --fill missing-urls.txt with a reviewed explicit
HTTPS URL list; it deduplicates the list and skips usable recorded entries. Run a
separate --replay afterwards. A pinned logical clock is not a historical measurement
of upstream state: new answers can change the results.
python tests/test_risk.py # engine regressions, offline, real upstream snapshots
python tests/test_mcp.py # MCP protocol conformance
python tests/test_upstream_contract.py # live: every path risk.py reads, against a measured baselineEvery case in tests/ is pinned to a defect that actually reached production.
The contract test earns its keep: VetAgent's worst bug was reading
simulationResult.isHoneypot when honeypot.is puts that flag in honeypotResult.
The key did not exist, the lookup returned None, it was read as False, and the
honeypot check silently passed every token it was ever asked about. No mocked test
could have caught that — only one that calls the real API and asserts the shape.
Rule for this repo: a commit that claims to fix something ships with a test that was red before it.
Cloudflare Python Worker, no heavy dependencies.
src/
entry.py HTTP routing (entry class must be named Default)
risk.py risk engine — assess / liquidity / new_pools
mcp_server.py hand-written streamable-http MCP endpoint (JSON-RPC 2.0)
landing.html landing page
bench/ accuracy benchmark (independent labels + ablation)
tests/ regression, protocol, and upstream-contract suites
docs/ agent integration guide, handoff, MCP registry manifestThe MCP endpoint is hand-written rather than using the official mcp package: that
package pulls in pydantic's C extensions, which do not install on Cloudflare Python
Workers. Plain JSON-RPC turned out to be smaller and fully client-compatible.
| Source | Used for |
|---|---|
| DexScreener | pairs, price, liquidity, volume, pair age |
| GeckoTerminal | liquidity fallback, new/trending pools |
| honeypot.is | buy/sell simulation, taxes, aggregate risk, contract openness -- Ethereum, BSC and Base only |
| RugCheck | Solana rug score, mint/freeze authority, Token-2022 extensions. On Solana, holder concentration is reported only when RugCheck supplies a holder list; missing lists remain a coverage gap. |
Identified liquidity-pool accounts are excluded when matching identities are available; otherwise the reported share may include pools. This check is unavailable on EVM.
GoPlus is not used by the engine — it is reserved as the benchmark's held-out oracle. Adding it to the engine requires giving the benchmark a new independent labeller first, or the accuracy numbers stop meaning anything.
Four documents, one job each. If something is in two of them, one of them is wrong.
| Document | Answers |
|---|---|
README.md (this file) | What is this, how do I call it |
docs/DECISIONS.md | Why is it built this way, and what enforces each rule |
docs/STRATEGY.md | Who pays, what the moat is, when to shut it down |
Why a change was made lives in the commit message, which is immutable and attached to the diff. Why a line of code looks odd lives in a comment next to that line. Neither gets copied into a document, because a copy rots without anyone noticing.
VetAgent reports observable on-chain risk. It is not financial advice, it does not
size positions, and it cannot see off-chain risk — team behaviour, social engineering,
or a rug executed through governance. Treat low as "no fatal signal found in the
checks that ran", never as "safe to buy".
MIT — see LICENSE.
Pick your client and paste the snippet. Each one is the same server, written the way that client expects it.
claude mcp add vetagent --transport http https://vetagent.dev/mcp{
"mcpServers": {
"vetagent": {
"url": "https://vetagent.dev/mcp",
"type": "http"
}
}
}code --add-mcp '{"name":"vetagent","url":"https://vetagent.dev/mcp","type":"http"}'Runs as a hosted service. Your client connects over the network and nothing is installed locally.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/vetagent to learn what the "VetAgent" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
claude mcp add --transport http vetagent https://vetagent.dev/mcp| Name | What it does |
|---|---|
assess_token_risk | Safety check to run BEFORE buying, holding, or recommending a token. Returns an actionable verdict (low / medium / high / unknown), a 0-100 risk score, and the individual signals behind it. Covers on |
get_token_liquidity | Liquidity snapshot for a token's primary trading pair: price, 24h volume, pair count and the chains it trades on. Check 'status' before using the numbers. 'ok' means usable upstream data, not independ |
find_new_hot_pools | Scan a chain for the newest and most active trading pools, returning name, token_address, price, liquidity, 24h volume and pool age. For active-pool queries, use listing=trending to select only the or |
Read live from the server on November 15, 2026.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/vetagent)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "vetagent" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.