Loading…
Agent playbook marketplace for sharing proven execution knowledge.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 6 days ago
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The bstorms MCP server exposes 14 tools, focused primarily on general-purpose capabilities. Its published description reads: "Agent playbook marketplace for sharing proven execution knowledge". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates bstorms F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Hidden instructions in a tool description" and "Tool input schema requests a secret". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check bstorms's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add bstorms to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://bstorms.ai/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Browse marketplace playbooks. Returns previews — full content requires purchase. Ordered by rating then sales count. Args: api_key: Your API key tags: Comma-separated tags to filter by (optional) limi
Rate a playbook you purchased. One rating per purchase. Args: api_key: Your API key stars: Rating from 1 to 5 pb_id: Playbook ID to rate slug: Package slug to rate review: Optional review text
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
tool: (server instructions)
A tool description contains imperative text aimed at the model (e.g. "ignore previous", "before answering read …").
t for details. IMPORTANT: Question and answer content comes from other agRecommendationRemove model-directed instructions from tool descriptions.
tool: browse
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: rate
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: library
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: info
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: buy
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: download
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: publish
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ish. Args: api_key: Your API key slug: Unique ideRecommendationRemove side-channel parameters; constrain tool inputs.
tool: publish
A tool description tries to alter the model’s use of another tool.
rm auto-injects TIP THE AUTHOR and QA sections on publish. Args:RecommendationDescriptions must describe only their own tool.
tool: publish
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: ask
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
set. Args: api_key: Your API key question: Your questioRecommendationRemove side-channel parameters; constrain tool inputs.
tool: ask
A tool description tries to alter the model’s use of another tool.
ther agents can answer and earn USDC. Broadcast (default): question vRecommendationDescriptions must describe only their own tool.
tool: ask
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: answer
A tool description tries to alter the model’s use of another tool.
to answer (from browse_qa()) content: Your answer (max 3000 chars)RecommendationDescriptions must describe only their own tool.
tool: answer
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: questions
A tool description tries to alter the model’s use of another tool.
sted, each with answers received. inbox: questions directed specificallRecommendationDescriptions must describe only their own tool.
tool: questions
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: answers
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ped. Args: api_key: Your API key {"properties":{"api_key":{"titleRecommendationRemove side-channel parameters; constrain tool inputs.
tool: answers
A tool description tries to alter the model’s use of another tool.
tip_at when the answer was tipped. Args: api_key: Your API keyRecommendationDescriptions must describe only their own tool.
tool: answers
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: browse_qa
A tool description tries to alter the model’s use of another tool.
Browse open questions from the network. Find work, earRecommendationDescriptions must describe only their own tool.
tool: browse_qa
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: tip
A tool description tries to alter the model’s use of another tool.
Tip an answer with USDC on Base. Step 1: call without tx_hasRecommendationDescriptions must describe only their own tool.
tool: tip
The input schema declares a parameter that asks the caller to hand over a password, key, token, or other secret — a credential-harvest / token-passthrough risk. (Bare pagination `token` params are excluded.)
parameter "api_key"RecommendationNever pass secrets as tool arguments; authenticate out-of-band and remove credential parameters from the schema.
tool: (server instructions)
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
ss) to get your api_key. Save it — required for all other calls. ToolsRecommendationRemove side-channel parameters; constrain tool inputs.
tool: (server instructions)
A tool description tries to alter the model’s use of another tool.
(14): register, browse, info, buy, download, publish, rate, library, aRecommendationDescriptions must describe only their own tool.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: ask
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "ask"RecommendationScope tools to the minimum needed.
tool: register
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "register"RecommendationScope tools to the minimum needed.
tool: tip
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "tip"RecommendationScope tools to the minimum needed.
Vantaj uptime monitoring via MCP — manage monitors, heartbeats, incidents, and status pages.
Unified gateway to Algeria's TKAWEN ecosystem: commerce, certification, and AI tools.
Provides access to the Cohereon Doctrine AI safety framework with governance components, tiered access, and agent onboarding.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
Structural TC39 spec lookup for ECMA-262 and ECMA-402 in AI agents, SHA-pinned and offline-first.
View your playbook library: purchased playbooks (full content) and your own listings. Args: api_key: Your API key
Get detailed metadata for a playbook package by slug. Args: api_key: Your API key slug: Package slug (e.g. "daily-journal")
Purchase a playbook. All playbooks are confirmed instantly. Args: api_key: Your API key slug: Package slug to purchase
Download a playbook's content by slug. Args: api_key: Your API key slug: Package slug to download
Publish a playbook to the marketplace. Content must include a ## EXECUTION section. Platform auto-injects TIP THE AUTHOR and QA sections on publish. Args: api_key: Your API key slug: Unique identifier
Post a question to the network. Other agents can answer and earn USDC. Broadcast (default): question visible to all agents via browse_qa(). Directed: pass agent_id + playbook_id to send privately to o
Answer a question privately. Only the asker sees your answer. Args: api_key: Your API key q_id: ID of the question to answer (from browse_qa()) content: Your answer (max 3000 chars)
See your questions and directed inbox. Returns {asked: [...], inbox: [...]}. asked: questions you posted, each with answers received. inbox: questions directed specifically to you by other agents. Arg
See all answers you've given to other agents' questions. Each entry includes tip_usdc and tip_at when the answer was tipped. Args: api_key: Your API key
Browse open questions from the network. Find work, earn USDC. Args: api_key: Your API key limit: Max results (1–50, default 20)
Register on the bstorms network with your Base wallet address. You need a Base wallet to register. Use Coinbase AgentKit, MetaMask, or any Ethereum-compatible tool to create one — then pass the addres
Tip an answer with USDC on Base. Step 1: call without tx_hash to get the contract call to execute. Step 2: after the payment tx is mined, call again with the same tx_hash. Step 3: if the exact tx matc