Skills/PyPI/toucan-payments-mcp

toucan-payments-mcp@1.0.3

VERIFIED· install only

Publisher claims: "Model Context Protocol (MCP) server for Toucan Payments online payment gateway APIs" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher toucan-payments-platform-engineering-engineering · publishing for 59 daysInstalls 64Last detonated 1 h ago
$claude mcp add toucan-payments-mcp -- uvx toucan-payments-mcp
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
7 of 7 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

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
LANGCHAIN_API_KEYTOUCAN_ACCESS_TOKENTOUCAN_WEBHOOK_SECRETConfiguration, not credentials: LANGCHAIN_PROJECT, LANGCHAIN_TRACING_V2, TOUCAN_ENV, TOUCAN_MERCHANT_NUMBER, TOUCAN_TERMINAL_NUMBER
Where it talks to
no vendor host named in the codeAlso testtoucanpay.in, toucanpay.in, langfuse.com — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names testtoucanpay.in, toucanpay.in, langfuse.com as well as its own vendor. The guard injects LANGCHAIN_API_KEY, TOUCAN_ACCESS_TOKEN, TOUCAN_WEBHOOK_SECRET only into requests to the host you bind (and its subdomains) and refuses the rest.

$vet-skills run --net declared -- uvx toucan-payments-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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 81/100 (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 · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'click'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ModuleNotFoundError: No module named 'httpx'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.2sprocessexited 1: ModuleNotFoundError: No module named 'pydantic'
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'prometheus_client'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocessexited 1: ModuleNotFoundError: No module named 'pydantic'
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'pydantic'
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sprocessexited 1: ModuleNotFoundError: No module named 'toucan_mcp'
0.4sprocess7 of 7 bundled scripts run with no arguments
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathssrc/toucan_mcp/cli.py:80 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system fileswithin the local `.env` file. Ensure this file is never committed to public VCS repositories.Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/cli.py:72 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files@click.option("--token", prompt=False, default=None, help="Toucan Payments Bearer access token (stored in plaintext .env)") # Token optionFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathspyproject.toml:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"python-dotenv>=1.0.1", # Utility to load environment variables from .env files seamlesslyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/cli.py:83 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconsole.print("[dim yellow]Security Notice: Bearer access token is saved in plaintext to .env[/dim yellow]\n") # Security noteFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/cli.py:89 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_path = Path(".env") # Target .env file pathFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/config.py:49 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=str(_ENV_FILE_PATH) if _ENV_FILE_PATH.is_file() else ".env", # Prefer absolute path to project root .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actionsrc/toucan_mcp/cli.py:205 · File type combined with upload action — agent may exfiltrate local data filesbackup_path = target_path.with_suffix(".json.bak") # Compute backup file pathFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathssrc/toucan_mcp/client.py:254 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesf"Toucan Keycloak JWT tokens expire after 30 minutes. Please refresh TOUCAN_ACCESS_TOKEN in .env with a fresh token from merchant portal DevTools."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/config.py:15 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesclass ToucanSettings(BaseSettings): # Application configuration model loaded from environment and .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/client.py:112 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesOtherwise, always reads fresh from the active environment / .env on every requestFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/client.py:180 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesf"Toucan Keycloak JWT tokens expire after 30 minutes. Please refresh TOUCAN_ACCESS_TOKEN in .env with a fresh token from merchant portal DevTools."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/toucan_mcp/telemetry.py:34 · Credential pass-through configuration — agent relays sensitive credentialssecret_key=settings.langfuse_secret_key, # Pass secret keyFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/toucan_mcp/config.py:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files_ENV_FILE_PATH = _PROJECT_ROOT / ".env" # Absolute path to project .env fileFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/config.py:21 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files3. Project-level `.env` file (resolved absolutely via project root)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/server.py:81 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesf"- **Fix:** Set these in `.env` / the process environment (or pass them as tool arguments), then retry." # RemediationFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/toucan_mcp/client.py:120 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Live runtime mode: dynamically load latest token from .env or os.environFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈61 tok
1 file · 14 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

No advisories in OSV for toucan-payments-mcp@1.0.3 as of 38 min ago. This is the package itself, not its dependencies.