canonical-ai-company-search
mcpsmitheryCanonical finds the companies others miss — the long tail. Unlike web search that returns links to crawl and rank, it's a verified company graph: describe what you want in plain English (or pass structured filters) and it retrieves from a corpus of millions, verifying each match against products, target customer, and business model with an LLM. Results come back keyed by domain, so an agent can walk the graph — search for companies, find look-alikes, pull a company's profile, disambiguate a name. Built for sales prospecting, recruiting, and market research.
By Smithery | 16 findings | Scanned 7/2/2026 | tooltrust-scanner/v0.3.19
Risk Summary
Safe With Normal ControlsExcessive Permissions is the main signal, but overall risk remains within an acceptable range.
Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.
Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.
Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.
Security Findings (16)
tool name "search_companies" implies read-only operation but declares exec permission
search_companiestool name "get_company_details" implies read-only operation but declares exec permission
get_company_detailsFix: Ensure tool names, descriptions, and permission declarations are internally consistent. Use explicit naming conventions that fully reflect actual capabilities.
search_companies:input schema exposes 20 properties (threshold: 10)
Fix: 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
search_companiesfind_similar_companiesget_company_detailsget_account_statusFix: 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.
declared capabilities: code/command execution, network access, filesystem access, HTTP requests
search_companiesdeclared capabilities: network access, filesystem access
find_similar_companiesdeclared capabilities: code/command execution, network access
get_company_detailsdeclared capabilities: network access
get_account_statusFix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.
Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.
search_companiesfind_similar_companiesget_company_detailslookup_companiesget_account_statusFix: 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 canonical-ai-company-search"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)