The MCP tool directory.
Each row is one tool from one provider. Tools sharing a name across providers (e.g. search) are listed separately because they aren't interchangeable.
[ 3127 tools indexed ]
[ all tools ]
30 / 3127
lookup_token_by_symbol
[ remote ]Search for token addresses by symbol or name. Returns multiple potential matches based on symbol or token name similarity. Only the first ``TOKEN_RESULTS_LIMIT`` matches from the Blockscout API are returned.
lotuswisdom
[ remote ]Contemplative reasoning tool. Use for complex problems needing multi-perspective understanding, contradictions requiring integration, or questions holding their own wisdom. **Workflow:** Always start with tag='begin' (returns framework). Then continue with contemplation tags. Do NOT output wisdom until status='WISDOM_READY'. **Tags:** begin (FIRST - receives framework), then: open/engage/express (process), examine/reflect/verify/refine/complete (meta-cognitive), recognize/transform/integrate/transcend/embody (non-dual), upaya/expedient/direct/gradual/sudden (skillful-means), meditate (pause).
ls_rlt_search
[ remote ]Related law search (관련법령 조회). This tool searches for laws related to a given query term. Part of the 법령정보 지식베이스, it identifies associations between laws based on shared subject matter or cross-references. Args: query: Search keyword (default "*") display: Number of results per page (max 100, default 20) page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" ctx: MCP context (injected automatically) Returns: Search results or error
lsDelegated_service
[ remote ]Retrieve delegated laws/rules/ordinances (위임 법령 조회). This tool retrieves information about laws, administrative rules, and local ordinances that are delegated by a parent law. Shows the delegation hierarchy and which specific articles delegate authority. ⚠️ Note: This API does NOT support HTML format (only XML/JSON). Args: id: Law ID (required if mst not provided) mst: Law master number (required if id not provided) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default) or "XML" (HTML not available for this endpoint) ctx: MCP context (injected automatically) Returns: Delegation hierarchy with delegated laws/rules/ordinances or error Examples: Retrieve delegations for 초·중등교육법: >>> lsDelegated_service(id="000900", type="XML")
lstrm_ai_search
[ remote ]Search legal terms using AI (법령용어 AI 조회). This tool searches Korean legal terminology using AI-powered semantic matching. Returns definitions and explanations of legal terms. Args: query: Search keyword (default "*") display: Number of results per page (max 100, default 20) page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" ctx: MCP context (injected automatically) Returns: Search results or error
lstrm_rlt_jo_search
[ remote ]Legal term to article linkage (법령용어→조문 연계 조회). This tool searches the linkage between legal terms and the specific law articles where those terms are used or defined. Args: query: Search keyword (default "*") display: Number of results per page (max 100, default 20) page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" ctx: MCP context (injected automatically) Returns: Search results or error
lstrm_rlt_search
[ remote ]Legal term to everyday term linkage (법령용어→일상용어 연계 조회). This tool searches the linkage between formal legal terms and their plain-language (everyday) equivalents. Useful for finding how legal terminology maps to everyday Korean. Args: query: Search keyword (default "*") display: Number of results per page (max 100, default 20) page: Page number (1-based, default 1) oc: Optional OC override (defaults to env var) type: Response format - "JSON" (default), "XML", or "HTML" ctx: MCP context (injected automatically) Returns: Search results or error
mail_add_rule
[ remote ]Add an allow or block rule. Use type ALLOW or BLOCK, scope RECEIVE/SEND/REPLY, and value as email or *@domain.com.
mail_get_attachment
[ remote ]Download the contents of an email attachment as base64-encoded data. Use mail.get_message or mail.get_thread first to find attachment IDs and metadata.
mail_list_messages
[ remote ]List emails in your agent's inbox. Returns newest first.
mail_list_threads
[ remote ]List email threads in your agent's inbox. Returns newest first.
mail_reply
[ remote ]Reply to an existing email in a thread. Supports up to 10 attachments (10 MB each, 25 MB total).
mail_send
[ remote ]Send an email from your agent's inbox. Supports up to 10 attachments (10 MB each, 25 MB total).
mail_update_thread_labels
[ remote ]Add or remove labels on a thread (e.g. 'starred', 'important', 'archived', or custom labels). Thread labels are separate from message labels. Labels must be 1-100 chars from [a-zA-Z0-9_-:.]. Max 20 labels per call. Removing a label deletes user data — use with care.
manage_notification_subscription
[ remote ]Manage a notification subscription: ignore, watch, or delete a notification thread subscription.
manage_repository_notification_subscription
[ remote ]Manage a repository notification subscription: ignore, watch, or delete repository notifications subscription for the provided repository.
management-brand-radar-prompts
[ remote ]Retrieves custom prompts for a specific brand radar report. Requests to this endpoint are free and do not consume any API units. Use doc tool first to get the real input schema.
management-keyword-list-keywords
[ remote ]Retrieves keywords from a keyword list. Requests to this endpoint are free and do not consume any API units. Use doc tool first to get the real input schema.
management-locations
[ remote ]Retrieves a list of management locations filtered by country code and optionally by US state. Use doc tool first to get the real input schema.
management-project-competitors
[ remote ]Retrieves the list of competitors associated with a specific Rank Tracker project in Ahrefs, using the project's unique identifier. Use doc tool first to get the real input schema.
management-project-keywords
[ remote ]Returns all tracked keywords for a specific Rank Tracker project, including associated tracking metadata. Use doc tool first to get the real input schema.
management-projects
[ remote ]Retrieves information about existing projects, including ownership, access type, presence of Rank Tracker keywords, and project ID. Use doc tool first to get the real input schema.
map-tiles
[ remote ]Get map tile URLs from the Macrostrat tiles server. Use lat-lng-to-tile tool first to get proper x,y coordinates. Defaults to 'carto' scale which automatically adapts detail level to zoom.
mcp.app.get
[ remote ]Retrieves a paginated list of Model Control Protocol (MCP) servers that are configured for a specific application or toolkit. This endpoint allows you to find all MCP server instances that have access to a particular application, such as GitHub, Slack, or Jira.
mcp.delete
[ remote ]Performs a soft delete on a Model Control Protocol (MCP) server, making it unavailable for future use. This operation is reversible in the database but cannot be undone through the API. Any applications or services connected to this server will lose access after deletion.
mcp.get
[ remote ]Retrieves detailed configuration information for a specific Model Control Protocol (MCP) server. The returned data includes connection details, associated applications, enabled tools, and authentication configuration.
mcp.score_server
[ remote ]Score an MCP server against the Revuo quality rubric. Pass either a product slug (scored from cached probe data on the product's direct-probe MCP entry; fast) OR an endpoint URL (probed live). Returns: { target, server, summary { coreAwarded/Max/Percent, extensionAwarded/Max/Percent, probedAt }, categories[] (ServerMetadata, CapabilityQuality, ConfigurationUX, RevuoExtensions), checks[] (every rubric check with awarded/max/passed/evaluated/fixSuggestion/evidence), topFixes[] (failed checks ranked by points-at-stake), probe (probe diagnostics) }. Core score (max 100) is Smithery-comparable. Extension score covers Revuo-specific signals (response time today; freshness, error envelope, schema stability are not yet implemented and report evaluated=false — excluded from totals, never counted as a failure). A check with evaluated=false is a Revuo gap, not the server's fault. Errors: { error: { code: 'bad_input'|'not_found', ... } }.
mcp.servers.create
[ remote ]Creates a new Model Control Protocol (MCP) server instance for the authenticated project. An MCP server provides a connection point for AI assistants to access your applications and services. The server is configured with specific authentication and tool permissions that determine what actions the connected assistants can perform.
mcp.servers.custom.create
[ remote ]Creates a new Model Control Protocol (MCP) server instance that can integrate with multiple applications or toolkits simultaneously. This endpoint allows you to create a server that can access tools from different applications, making it suitable for complex workflows that span multiple services.
mcp.servers.generate.create
[ remote ]Generates a Model Control Protocol (MCP) URL for an existing server with custom query parameters. The URL includes user-specific parameters and configuration flags that control the behavior of the MCP connection.