Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@veragent-mcp Is the playwright-mcp server safe?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
The trust layer for MCP — as an MCP tool. Let Claude (or any MCP client/agent) check whether an MCP tool is safe before installing it, look up the most trusted tools, or score an entire MCP stack — all backed by the Veragent trust registry.
⭐ Star this repo ·
uvx veragent-mcp— check any tool's trust before you install · Get your tool SGC Certified → · How we audit (open methodology) →
Tool | What it does |
| Veragent trust score + audit state for a tool/server/agent. Use before installing. |
| The most trusted MCP tools, optionally filtered. |
| Score a whole |
Related MCP server: agentforge-trust-mcp
Add to your claude_desktop_config.json:
{
"mcpServers": {
"veragent": {
"command": "uvx",
"args": ["veragent-mcp"]
}
}
}Then ask Claude: "Is the playwright-mcp server safe? Check Veragent."
uvx veragent-mcp
# or
pip install veragent-mcp && veragent-mcpVERAGENT_API_BASE — override the API base (default https://veragent.store/api/v1).
Veragent labels static-analysis results as Heuristic and reserves SGC Certified for behavioral-sandbox passes. Scores are reported with this distinction.
Check the Veragent trust score and audit state of an MCP tool / server / agent by name. Use this BEFORE installing or recommending an MCP tool to verify it is safe.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavior. It mentions checking trust score and audit state but does not detail the response format, whether it's a read-only operation, or any side effects. Adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no redundant information. The action verb 'Check' is front-loaded, and every word adds value. Highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and an output schema (assumed to document return values), the description is nearly complete. A minor gap is lack of behavioral details, but overall sufficient for an agent to use effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only one parameter 'name' with 0% schema documentation. The description adds 'by name', clarifying the parameter's role, but does not provide format or examples. Compensates partially for the lack of schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it checks the Veragent trust score and audit state for a named MCP tool/server/agent. This distinguishes it from siblings like 'list_trusted_tools' (listing) and 'scan_mcp_stack' (scanning), providing a specific verb+resource.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly instructs to use 'BEFORE installing or recommending an MCP tool to verify it is safe', giving clear context for when to use. While no explicit when-not or alternatives, the sibling names imply alternatives for other tasks.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the most trusted MCP tools, optionally filtered by a search query.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | * | |
| limit | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behaviors. It only mentions listing with optional filter; no info on trust criteria, authentication requirements, side effects, or output behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence, no fluff. However, it sacrifices completeness for brevity, which is acceptable for a simple tool but could be more informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with 2 simple params and no output schema, the description provides the core action but omits output details (e.g., list structure, pagination) and trust definition. Adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, description must compensate. It explains the query parameter superficially ('optionally filtered by a search query') but does not describe the limit parameter or the expected format/behavior of the query.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function: listing the most trusted MCP tools with optional search filtering. It distinguishes from siblings like check_tool_trust (specific trust check) and scan_mcp_stack (stack scan).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus siblings. Lacks context for when filtering is appropriate or any caveats.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Score a whole MCP stack for security. Pass a parsed mcp_settings.json object (or just its mcpServers block). Returns per-server risk levels and a summary.
| Name | Required | Description | Default |
|---|---|---|---|
| mcp_config | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It describes the action (security scoring) and output (risk levels, summary) but omits side effects, authorization needs, or rate limits. Adequate but not robust for a read-like operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. The main purpose is front-loaded and every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description appropriately summarizes return values. It covers the essential input and output for the tool's complexity. Could optionally mention prerequisites but not required.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 0% schema description coverage, the description adds meaning by specifying the parameter should be a 'parsed mcp_settings.json object (or just its mcpServers block)', which clarifies the expected shape beyond the generic 'object' type.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Score' and clearly identifies the resource 'whole MCP stack' along with the input ('mcp_settings.json') and output ('per-server risk levels and a summary'). It implicitly distinguishes from siblings which focus on individual tool trust.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use: when you have a parsed mcp_settings.json object or its mcpServers block. Does not provide explicit exclusions or direct comparisons to sibling tools, but the context makes the intended use clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0check_tool_trustlist_trusted_toolsscan_mcp_stackScored across 3 tools
Each tool has a distinct purpose: checking a single tool, listing trusted tools, and scanning a full stack. No overlap.
All tool names follow the consistent verb_noun pattern with snake_case, making them predictable.
Three tools is appropriate for a security verification server, covering individual check, listing, and stack scan without excess.
The tool surface covers the main verification operations, though a detailed audit or reporting tool could enhance completeness.
Trust checks for MCP servers: trust scores, tool-drift detection, signed diligence receipts. Free.
Trust infrastructure for AI agents. Check an AI agent or endpoint before invocation using reliability monitoring, endpoint verification, reputation signals, and a machine-readable trustDecision. Includes a read-only MCP trust check by URL with no AgentTrust API key required.
Pre-connect trust checks for AI agents and MCP servers using HVTracker's public trust registry.
Signed, offline-verifiable safety scores for the MCP servers, packages & tools an agent connects to
