andysalvo-agentic-platform
mcpsmitheryFree diagnostic tools for AI agents and MCP servers. No API key needed. The only MCP linter that exists. Validate your tool definitions for anti-patterns, missing descriptions, and schema issues. Plus governance scoring (0-100), cost estimation across all major models, and trust evaluation for any MCP server. Free Tools: - mcp_manifest_lint -- Validate MCP tool definitions. Pass/fail report with fixes. - agent_health_check -- Score your agent's system prompt on 17 governance best practices. - estimate_agent_cost -- Compare costs across Claude, GPT, Gemini, Llama, Mistral, and 20+ models. - evaluate_service -- Check any MCP server's trustworthiness before spending money. Expert Skills (10 free calls/day): Curated context packages for governance, agentic economics, and intent architecture. Register for a free API key to start. Connect: https://api.asalvocreative.com/mcp
By Smithery | 28 findings | Scanned 4/19/2026 | tooltrust-scanner/v0.3.8
Risk Summary
Needs ApprovalExcessive Permissions plus Dep Visibility raises enough risk that this tool should not be auto-trusted.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
Recommended action: Keep this tool behind manual approval and avoid unattended runs until the risky capabilities are narrowed or removed.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (28)
tool declares exec permission
registerestimate_agent_costevaluate_servicetool declares network permission
buy_creditsevaluate_serviceFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
input parameter "api_key" appears to accept a secret or credential
list_skillsget_skillcheck_usagebuy_creditsinput parameter "input_tokens" appears to accept a secret or credential
estimate_agent_costinput parameter "output_tokens" appears to accept a secret or credential
estimate_agent_costFix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.
tool declares fs permission
registerlist_skillsget_skillbuy_creditsFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration
registerbuy_creditsestimate_agent_costevaluate_serviceFix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
registerlist_skillsget_skillcheck_usagebuy_creditsagent_health_checkmcp_manifest_lintestimate_agent_costevaluate_serviceFix: Review and remediate the identified issue.
Scan this tool yourself
Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.
Install once, then scan any MCP server:
$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash$ tooltrust-scanner scan --server "npx -y andysalvo-agentic-platform"Adjust the package name if your npm registry name differs from the tool ID. View source
Add badge to your README
Copy this Markdown to show your ToolTrust grade on GitHub.
[](https://github.com/AgentSafe-AI/tooltrust-directory)