Skills/PyPI/sra-riskgate-mcp

sra-riskgate-mcp@0.20.0

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 46 daysInstalls 3,674Last detonated 28 min 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_NEW_COUNTERPARTY, SRA_POLICY_FILE, SRA_RECEIPT_CHAIN_FILE, SRA_RECEIPT_KEY, SRA_RECEIPT_KEY_ID, SRA_RPC_URL, SRA_SCREENING_HOLD_AT, SRA_SCREENING_REJECT_AT, SRA_TIMEOUT
Where it talks to
no vendor host named in the code
What we saw when it ran
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 0.18.1

vet-skills diff sra-riskgate-mcp 0.18.1 0.20.0

In the sandbox, this version reached for nothing 0.18.1 did not. Compared from the two recorded runs, not from source.

0.18.1 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 2026-11-22 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
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationsrc/sra_riskgate_mcp/server.py:1296 · 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 attemptREADME.md:38 · 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
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
LOW
Prompt injection attemptREADME.md:314 · 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
LOW
Prompt injection attemptCHANGELOG.md:317 · 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
HIGH
Credential pass-through configurationsrc/sra_riskgate_mcp/server.py:875 · 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

Cost to the agent

Instructions loaded
≈66 tok
1 file · 38 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

Not checked against OSV yet; the weekly check has not reached this version.