Agent Wormhole MCP server
io.github.runningoffcode/wormhole-x402·v0.8.0·5 starsCheck tokens, pages and x402 payments before your agent trusts them. Offline verdicts.
5 stars697 downloads/wk
Reviews
Write oneNobody has reviewed Agent Wormhole yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Agent Wormhole tools (5)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
check_before_useCheck anything BEFORE trusting it — a web page you are about to read,
check_tokenCheck a token launch BEFORE reading its metadata. A token's name,
scan_textScan untrusted text or a JSON document (a 402 quote body, a merchant
verify_deliveryCheck what a PAID request actually delivered, AFTER the payment — the
verify_paymentCheck an x402 payment against the merchant's quote BEFORE signing it.
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- Code scan29 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 qualitystatic API keys via environment variables6/15
- Maintenancelast push 21 days ago15/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Agent Wormhole compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 83/100
- higher than 68% of 4,461 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
- GitHub stars
- 5
- more than 78% of 2,713 AI and agents servers
- Downloads a week
- 697
- more than 90% of 1,554 AI and agents servers with a package
What its tools let an agent do: 5 read
Install Agent Wormhole in Claude Code, Cursor or VS Code
Runs npx -y wormhole-x402 on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add wormhole-x402 -- npx -y wormhole-x402
What the publisher says
From the Agent Wormhole repository's README, as published. We do not edit it. Read it on GitHub
Agent Wormhole
Integration guide: payment safety, policy, confirmed top-ups and launch attestations.
The security layer for agentic commerce.
agentwormhole.com · docs · dashboard · research
AI agents now read instructions they did not write, sign payments a merchant priced, and buy tokens whose metadata an attacker typed. All three are the same problem — untrusted text reaching a model that acts — and this is one stack that covers all three:
Everything verifiable is free forever — badges, attestations, signatures, verdicts. The metered work is what costs, in USDC over x402, and an agent can pay for itself with no human in the loop.
Quickstarts
Protect a coding agent — 30 seconds, offline, free
pipx install wormhole-guard
wormhole scan ~/your-project --blast-radius # what is there now
wormhole init ~/your-project # harden + baseline (dry run until --apply)CRITICAL SessionStart hook executes a script from an unusual path [AUTOSTART-002]
.claude/settings.json
`node .github/setup.js` runs unprompted on SessionStart. This survives
uninstalling the package that planted it.No account, no API token, no network call. Your CLAUDE.md never leaves the machine. Then wire the three hooks — what arrives, what leaves, what persists:
wormhole readguard --install # inbound: fetched pages, shell output, MCP responses
wormhole outbound --install # outbound: refuse to pass a payload on
wormhole guard --install # writes: the PreToolUse hookGive any MCP agent the check-first habit
Claude Code, Cursor, any MCP host — five tools, including checktoken (check a token launch before reading its metadata) and checkbefore_use (check a page, manifest, or listing before trusting it):
{
"mcpServers": {
"wormhole": {
"command": "npx",
"args": ["-y", "wormhole-x402", "mcp"],
"env": { "WORMHOLE_API_KEY": "awk_..." }
}
}
}Without a key the tools run locally and read the free registry; with one, unobserved tokens are scanned on demand.
Agent-native API — register and arrive funded, one call
No GitHub, no browser, no human. Attach an x402 payment (USDC on Base or Solana) and the new tenant is born funded:
curl -X POST https://dashboard.agentwormhole.com/api/v1/register \
-H "content-type: application/json" \
-H "X-PAYMENT: <base64 x402 payment>" \
-d '{"name":"my trading agent"}'
# → { "api_key": "awk_…", "balance_micro_usdc": "1000000", ... }Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Agent Wormhole: common questions
- Is Agent Wormhole MCP server safe?
- Mostly: it is graded B (83/100). Read the Agent Wormhole safety report
- How do I install Agent Wormhole?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Agent Wormhole need an API key?
- Yes. The registry entry asks for
WORMHOLE_API_KEY. - Is Agent Wormhole maintained?
- The last commit was 42 days ago (2026-09-25). The latest release is v0.8.0.
- What can I use instead of Agent Wormhole?
- Servers from other publishers that do the same job: Doc Bridge MCP server, Commonly MCP server and Decionis MCP server.
- How does Agent Wormhole compare with other AI and agents MCP servers?
- safety score 83/100 (higher than 68% of 4,461 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 Agent Wormhole
Same job from other publishers: the closest match first, then the best rated.
- Doc BridgeResolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.not reviewedEstablishedA
- CommonlyRead Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.not reviewedEstablishedA
- DecionisAuthorize consequential AI agent actions before executionnot reviewedEstablishedA
- mcptoonMCP tools + agent skills in one zero-dependency CLI: 71,929 -> 581 tokens (-99.2%, measured).not reviewedEstablishedA
- llmtrimMCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.not reviewedEstablishedA