sablier-mcp@0.13.2
CAUTION· not startedPublisher claims: "Sablier MCP — plug Wall Street-grade portfolio analytics, stress-testing, and SEC filing intelligence into any AI assistant. What takes quants & analysts weeks, done in 2 minutes." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
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: Caution 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
MCP_TOKEN_SECRETSABLIER_API_KEYor--allow-unauthenticated/--set-secretsConfiguration, not credentials: MCP_ISSUER_URL, MCP_PORT, MCP_TRANSPORT, SABLIER_API_URL- Where it talks to
- sablier-ai.com, sablier.ai (its own)Also run.app — not the publisher's domain; check what for before connecting.
- 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, and read the third-party hosts first. The code names run.app as well as its own vendor. The guard injects MCP_TOKEN_SECRET, SABLIER_API_KEY only into requests to sablier-ai.com (and its subdomains) and refuses the rest.
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 2026-11-16 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL with embedded credentials; URL with embedded credentials; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
4. In a new chat, activate via **"+" -> More -> Developer Mode**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.### Option B: ChatGPT (Developer Mode)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.1. Go to **Settings -> Developer Mode** and enable itFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.4. In a new chat, activate via **"+" -> More -> Developer Mode**Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.<link href="https://fonts.googleapis.com/css2?family=Source+Sans+3:wght@400;500;600;700&display=swap" rel="stylesheet">Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<link href="https://fonts.googleapis.com/css2?family=Source+Sans+3:wght@400;500;600;700&display=swap" rel="stylesheet">Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.### Option B: ChatGPT (Developer Mode)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.detail = resp.json().get("detail", "Invalid input. Please check your fields.")Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.1. Go to **Settings -> Developer Mode** and enable itFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.<input type="password" name="password" required placeholder="Enter your password" minlength="8">Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.Cost to the agent
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.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim sablier-it: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.