Loading…
Proxy server that forwards requests to the prompts.chat API, providing access to a curated collection of prompts with search and filtering capabilities by keyword, type, category, and tag.
Do not connect
A critical issue was found. Do not connect this server as-is.
Scanned 9 days ago Due for re-check
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 prompts-chat MCP server exposes 10 tools, focused primarily on filesystem and AI capabilities. Its published description reads: "Proxy server that forwards requests to the prompts.chat API, providing access to a curated collection of prompts with search and filtering capabilities by keyword, type, category,…". It communicates over Streamable HTTP using the 2025-06-18 protocol revision, and does not require authorization to connect. MCPGrade currently rates prompts-chat F — a critical issue was found and the server should not be connected as-is. Its most notable findings include "Data-exfiltration parameters" and "Data-exfiltration parameters". 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 prompts-chat's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add prompts-chat to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://prompts.chat/api/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.
Search for AI prompts by keyword. Returns matching prompts with title, description, content, author, category, and tags. Use this to discover prompts for various AI tasks like coding, writing, analysi
Get a prompt by ID and optionally fill in its variables. If the prompt contains template variables (like {{variable}}), you will be asked to provide values for them.
Save a new prompt to your prompts.chat account. Requires API key authentication. Prompts are private by default unless configured otherwise in settings.
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: save_prompt
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
count. Requires API key authentication. Prompts are private by defaultRecommendationRemove side-channel parameters; constrain tool inputs.
tool: save_skill
A tool exposes a free-text/webhook/feedback parameter with no honest purpose — a classic exfil channel.
files. Requires API key authentication. If the file contents are too loRecommendationRemove side-channel parameters; constrain tool inputs.
tool: save_skill
A tool description tries to alter the model’s use of another tool.
iles. Then call add_file_to_skill tool per file.RecommendationDescriptions must describe only their own tool.
tool: remove_file_from_skill
Tools that execute commands / write files / make arbitrary requests are exposed without annotations or guards.
file_from_skill Remove File from Skill Remove a file from an existing AgentRecommendationAnnotate destructive tools and require human approval.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
tool: update_skill_file
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "update_skill_file"RecommendationScope tools to the minimum needed.
tool: remove_file_from_skill
The server advertises open-world / broadly-scoped capabilities.
no annotations on write-capable tool "remove_file_from_skill"RecommendationScope tools to the minimum needed.
tool: remove_file_from_skill
One tool both accesses the filesystem and reaches the network. Combining two capability classes in a single tool widens its blast radius and is the substrate for confused-deputy and exfiltration abuse.
file_from_skill Remove File from Skill Remove a file from an existing AgentRecommendationSeparate filesystem and network capabilities into distinct, independently-scoped tools.
tool: remove_file_from_skill
A filesystem tool exposes a path parameter that is a free-form string with no pattern/enum/format constraint, so it accepts absolute paths and "../" traversal. A tool that constrains its path (a rooted `pattern` or an `enum`) does not fire.
unconstrained path parameter "filename"RecommendationConstrain the path parameter to a rooted allow-list and reject absolute/traversal paths server-side.
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.
Transform a basic prompt into a well-structured, comprehensive prompt using AI. Optionally searches for similar prompts for inspiration. Supports different output types (text, image, video, sound) and
Save a new Agent Skill to your prompts.chat account. Skills are multi-file prompts that can include SKILL.md (required), reference docs, scripts, and configuration files. Requires API key authenticati
Add a new file to an existing Agent Skill. Use this to add reference docs, scripts, or configuration files to a skill you own.
Update an existing file in an Agent Skill. Use this to modify reference docs, scripts, configuration files, or SKILL.md content.
Remove a file from an existing Agent Skill. Cannot remove SKILL.md as it is required.
Get an Agent Skill by ID, including all its files (SKILL.md, reference docs, scripts, etc.). Returns the skill metadata and file contents. Save to .claude/skills/{slug}/SKILL.md and .claude/skills/{sl
Search for Agent Skills by keyword. Returns matching skills with title, description, author, and file list. Use this to discover reusable AI agent capabilities for coding, analysis, automation, and mo