Skills/PyPI/sra-riskgate-mcp

sra-riskgate-mcp@0.18.1

VERIFIED· not started

Publisher claims: "MCP server: the pre-sign firewall for AI agents that pay. Approve, hold or reject stablecoin and x402 payments" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher sriram1983007-dev · publishing for 43 daysInstalls 3,329Last detonated 9 h ago
$claude mcp add sra-riskgate-mcp -- uvx sra-riskgate-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
SRA_ALLOWED_TOKENSSRA_API_KEYSRA_CHAINALYSIS_API_KEYSRA_ELLIPTIC_API_KEYSRA_ELLIPTIC_API_SECRETSRA_EXTRA_TOKENSSRA_EXTRA_TOKENS_FILESRA_RANGE_API_KEYSRA_TRM_API_KEYSRA_WEBACY_API_KEYConfiguration, not credentials: SRA_ALLOW_ACCOUNT_DEPLOYMENT, SRA_BASE_URL, SRA_CIRCLE_WALLETS, SRA_LEDGER_FILE, SRA_LOOKALIKE_CHECK, SRA_MAX_ALLOWANCE, SRA_MODEL, SRA_POLICY_FILE, SRA_RECEIPT_KEY, SRA_RECEIPT_KEY_ID, SRA_SCREENING_HOLD_AT, SRA_SCREENING_REJECT_AT, SRA_TIMEOUT
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 SRA_ALLOWED_TOKENS, SRA_API_KEY, SRA_CHAINALYSIS_API_KEY, SRA_ELLIPTIC_API_KEY, SRA_ELLIPTIC_API_SECRET, SRA_EXTRA_TOKENS, SRA_EXTRA_TOKENS_FILE, SRA_RANGE_API_KEY, SRA_TRM_API_KEY, SRA_WEBACY_API_KEY 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 -- uvx sra-riskgate-mcp

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

What changed since 0.12.0

vet-skills diff sra-riskgate-mcp 0.12.0 0.18.1

This version reaches for something 0.12.0 did not: 10 new credential variables (SRA_ALLOWED_TOKENS, SRA_API_KEY, SRA_CHAINALYSIS_API_KEY, SRA_ELLIPTIC_API_KEY, …). Compared from the two recorded runs, not from source.

New credential variables
SRA_ALLOWED_TOKENS, SRA_API_KEY, SRA_CHAINALYSIS_API_KEY, SRA_ELLIPTIC_API_KEY, SRA_ELLIPTIC_API_SECRET, SRA_EXTRA_TOKENS, SRA_EXTRA_TOKENS_FILE, SRA_RANGE_API_KEY, SRA_TRM_API_KEY, SRA_WEBACY_API_KEY

0.12.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 2026-11-18 and scored it 87/100 (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 · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1 ·
0.1sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.1sprocessscript backend runs setup only
0.1sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationsrc/sra_riskgate_mcp/server.py:804 · Credential pass-through configuration — agent relays sensitive credentialsserver enables them (SRA_ALLOWED_TOKENS), pass token for USDT (Ethereum), USDB (Ethereum, Base) or USDGFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
LOW
Prompt injection attemptREADME.md:35 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction fileown verification, such as "risk level: low (verified offline)", "pre-approved" or "ignore previousFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attemptREADME.md:282 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file"ignore previous instructions") and returns `hold` without asking the model if it finds one. On theFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Access to sensitive file pathstests/test_server.py:333 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files@pytest.mark.parametrize("url", ["file:///etc/passwd", "ftp://host/v1", "gopher://x", "javascript:alert(1)"])Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/sra_riskgate_mcp/server.py:1224 · Credential pass-through configuration — agent relays sensitive credentialsUSDC events are read, so facilitator batches and ERC-4337 bundles work too. For another stablecoin pass token:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
LOW
Prompt injection attemptCHANGELOG.md:289 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file("risk level: low (verified offline)", "pre-approved", "ignore previous instructions"), the payment isFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈66 tok
1 file · 37 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 sra-riskgate-mcp@0.18.1 as of 8 h ago. This is the package itself, not its dependencies.