← Back to search

io.github.daedalus/mcp-server-find

daedalus Scanned 13d ago

MCP server discovery - find and install MCP servers from Official Registry, Glama, and Smithery

C
74.5 / 100

Versions

0.1.0latest
first seen Jun 5, 2026
0.1.1
first seen May 19, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 4

search_mcp_servers
annotations: none low

Search for MCP servers by keyword, technology, or use case. Call this first whenever the user needs a capability you do not already have. Use it when the user mentions an external service, a database, a filesystem, or asks 'can you connect to X?'. Examples: - query='postgres' for PostgreSQL database - query='slack' for Slack integration - query='filesystem' for file system access Args: query: Search query - keyword, use case, or technology limit: Maximum results to return (1-50, default: 10) transport_type: Filter by transport type (stdio, streamable-http, sse, any) registry_type: Filter by package registry type (npm, pypi, oci, any) registry_source: Filter by registry source (official, glama, smithery, any) Returns: Formatted search results with metadata

limit int query str registry_type str transport_type str registry_source str
get_server_details
annotations: none low

Get detailed information about an MCP server. Always call this before recommending or installing a server. Returns metadata for judging safety and fit. Args: name: Server name or slug (e.g., 'io.modelcontextprotocol/filesystem') Returns: Detailed server information including trust signals, warnings, environment variables, and tools

name str
get_install_config
annotations: none low

Generate install config for a target client. Use this after get_server_details to generate a ready-to-paste JSON config. Args: name: Server name or slug platform: Target platform (claude-desktop, cursor, claude-code, cline, windsurf) Returns: JSON config snippet with file paths and required env vars

name str platform str
browse_categories
annotations: none low

Browse MCP server categories. Call with no category to list all categories with counts. Call with a category to get top servers in that category. Args: category: Optional category name (omit to list all) limit: Maximum results when category provided (1-50, default: 20) Returns: Category list or servers in a category

limit int category str

Permissions 4

database medium
Server uses database capabilities via: sqlite3
env_vars low
Server uses env_vars capabilities via: os.environ
network medium
Server uses network capabilities via: httpx, urllib
filesystem low
Server uses filesystem capabilities via: open(), os

Scan Findings 21

low
Tool 'search_mcp_servers' has no annotations annotation_checker · 100%
low
Tool 'get_server_details' has no annotations annotation_checker · 100%
low
Tool 'get_install_config' has no annotations annotation_checker · 100%
low
Tool 'browse_categories' has no annotations annotation_checker · 100%
info
Sandbox failed to start for behavioral verification behavioral_verifier · 100%
info
pyproject.toml metadata manifest_parser · 100%
info
No dependency files found for SBOM generation sbom_generator · 100%
info
Tool: search_mcp_servers manifest_parser · 90%
info
Tool: get_server_details manifest_parser · 90%
info
Tool: get_install_config manifest_parser · 90%
info
Tool: browse_categories manifest_parser · 90%
info
Transport: streamable-http manifest_parser · 80%
info
Required env vars (2) manifest_parser · 80%
info
Sandbox failed to start for output poisoning scan output_poisoning · 100%
medium
Permission: network access detected permission_analyzer · 90%
low
Permission: filesystem access detected permission_analyzer · 80%
medium
Permission: database access detected permission_analyzer · 90%
low
Permission: env_vars access detected permission_analyzer · 90%
critical
Tool poisoning in 'get_server_details': Directive language: 'always' poisoning · 85%
critical
Tool poisoning in 'get_server_details': Cross-tool sequencing directive poisoning · 85%
medium
No build provenance detected (SLSA L0) slsa_assessor · 90%