Skills/npm/mcp

mcp@0.14.0-alpha.0

VERIFIED· not started

Publisher claims: "Haven MCP server for local, non-custodial AI-agent payments — pay x402 (HTTP 402) APIs within on-chain-enforced budgets." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher haven_ai · publishing for 172 daysInstalls 11,939Last detonated 32 h ago
$claude mcp add mcp -- npx -y @haven_ai/mcp
WatchReport an issue

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
HAVEN_API_KEYHAVEN_CREDENTIALSConfiguration, not credentials: HAVEN_AGENT_ID, HAVEN_API_URL, HAVEN_CHAIN_ID, HAVEN_DELEGATE_KEY, HAVEN_MCP_ACK, HAVEN_NETWORK
Where it talks to
no vendor host named in the code
What the honeypot saw
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it with a scoped credential, under the guard. It asks for HAVEN_API_KEY, HAVEN_CREDENTIALS and talks to its vendor. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --net declared -- npx -y @haven_ai/mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-13 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 62 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
60sprocessdependency install exceeded 60s
60sclaimednot started: dependency install timed out; the server itself was not observed
60sprocessscript backend runs setup only
60sprocessno install scripts to re-run

Static findings

MEDIUM
Unicode escape sequence detecteddist/cli.cjs:1383 · Unicode escape sequence detected — may contain obfuscated payloads…6); } function renderConsentBlock(input, hash) { const lines = [ "", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/cli.cjs:1385 · Unicode escape sequence detected — may contain obfuscated payloads…00\u2500\u2500\u2500", "Haven MCP server \u2014 first-launch consent", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u250…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/index.cjs:1431 · Unicode escape sequence detected — may contain obfuscated payloads…ntial file (sidecar <credentials>.ack.json)."); lines.push(""); lines.push("\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/index.cjs:1383 · Unicode escape sequence detected — may contain obfuscated payloads…6); } function renderConsentBlock(input, hash) { const lines = [ "", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/cli.cjs:1431 · Unicode escape sequence detected — may contain obfuscated payloads…ntial file (sidecar <credentials>.ack.json)."); lines.push(""); lines.push("\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/index.js:1381 · Unicode escape sequence detected — may contain obfuscated payloads…6); } function renderConsentBlock(input, hash) { const lines = [ "", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/index.js:1383 · Unicode escape sequence detected — may contain obfuscated payloads…00\u2500\u2500\u2500", "Haven MCP server \u2014 first-launch consent", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u250…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/cli.js:1702 · npx invocation of non-well-known package — may execute untrusted code" npx @haven_ai/mcp --credentials /path/to/agent.json",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagedist/cli.cjs:1705 · npx invocation of non-well-known package — may execute untrusted code" npx @haven_ai/mcp --identity /path/to/identity.json --signer /path/to/signer.json",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/index.js:1429 · Unicode escape sequence detected — may contain obfuscated payloads…ntial file (sidecar <credentials>.ack.json)."); lines.push(""); lines.push("\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/index.cjs:1385 · Unicode escape sequence detected — may contain obfuscated payloads…00\u2500\u2500\u2500", "Haven MCP server \u2014 first-launch consent", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u250…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/cli.js:1703 · npx invocation of non-well-known package — may execute untrusted code" npx @haven_ai/mcp --identity /path/to/identity.json --signer /path/to/signer.json",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/cli.js:1429 · Unicode escape sequence detected — may contain obfuscated payloads…ntial file (sidecar <credentials>.ack.json)."); lines.push(""); lines.push("\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Unicode escape sequence detecteddist/cli.js:1383 · Unicode escape sequence detected — may contain obfuscated payloads…00\u2500\u2500\u2500", "Haven MCP server \u2014 first-launch consent", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u250…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
npx invocation of non-well-known packagedist/cli.cjs:1704 · npx invocation of non-well-known package — may execute untrusted code" npx @haven_ai/mcp --credentials /path/to/agent.json",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Unicode escape sequence detecteddist/cli.js:1381 · Unicode escape sequence detected — may contain obfuscated payloads…6); } function renderConsentBlock(input, hash) { const lines = [ "", "\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\u2500\…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)dist/index.d.ts:474 · MCP server using network transport (SSE/HTTP) — data sent over network…ntialAllowance, type HavenCredentialFile, type HavenCredentialSource, type HavenMcpServerOptions, type HavenMcpToolName, MCP_NAME, MCP_VERSION, SIGNER_CAPABILITY_KEY, TASK_BUDGET_MIN_SIGNER_VERSION, type ToolFailure, type ToolPayload, type…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈68 tok
1 file · 9 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for @haven_ai/mcp@0.14.0-alpha.0 as of 30 h ago. This is the package itself, not its dependencies.