The MCP tool directory.

This endpoint creates or updates an account subscription for a specific business service in PagerDuty. It allows users to manage subscription settings, such as notification preferences or service-level agreements, for a particular business service identified by its unique ID. Use this endpoint when you need to set up new subscription configurations or modify existing ones for a business service. The endpoint is particularly useful for automating subscription management across multiple business services or integrating subscription updates with other systems. Note that this operation may affect billing or service access, so it should be used carefully and with proper authorization.

Creates a new Alert Grouping Setting in PagerDuty, defining how alerts will be automatically grouped into incidents based on specified configurations. This endpoint allows users to set up intelligent alert grouping rules, improving incident management efficiency by reducing noise and consolidating related alerts. It's particularly useful for teams looking to streamline their incident response process and minimize alert fatigue. The setting can be applied to one or multiple services, with the option to use content-based or intelligent grouping algorithms.

Retrieves and aggregates analytics metrics for incidents related to escalation policies in PagerDuty. This endpoint allows for detailed filtering and customization of incident data, enabling users to analyze trends, performance, and patterns in their incident management process. It's particularly useful for generating reports, identifying areas for improvement, and understanding the effectiveness of escalation policies over time. The endpoint supports various filtering options, time zone specifications, and time-based aggregation, making it a powerful tool for operational insights and decision-making in incident management.

The AnalyzeResponderMetrics endpoint aggregates and analyzes responder performance metrics for PagerDuty incidents. It provides insights into response times, efficiency, and workload distribution. This tool is ideal for assessing and optimizing incident response processes, offering flexible filtering options for focused analysis. Note that it provides aggregated data, not real-time information, with a maximum analysis range of one year.

Creates a new change event in the PagerDuty system. This endpoint allows you to record and track significant changes or updates within your infrastructure or services. Use this when you want to log important modifications, deployments, or system alterations that may impact incident management or operational processes. The change event data can be used for correlation with incidents, providing context for potential issues or for auditing purposes. This endpoint is particularly useful for maintaining a comprehensive change log and enhancing the incident response process by providing additional context about recent system changes.

Creates a new cache variable within a PagerDuty event orchestration. This endpoint allows you to define a cache variable that can store dynamic data related to events, either based on recent values extracted from event fields or by counting trigger events within a specified time range. Cache variables are useful for maintaining state across multiple events and can be used in event routing and automation rules. The created cache variable can be configured with conditions to determine when it should be updated and can be optionally disabled. This tool should be used when setting up complex event orchestrations that require stateful processing or when implementing advanced automation workflows in PagerDuty.

This endpoint retrieves analytics metrics for responder teams based on incident data in PagerDuty. It allows for detailed filtering and customization of the data set, enabling users to analyze team and responder performance across various dimensions such as time range, urgency, priorities, and specific teams or responders. The endpoint is particularly useful for generating reports, assessing team efficiency, and identifying trends in incident management. It should be used when comprehensive analytics on responder team performance are needed, especially for large-scale or complex incident management scenarios. However, it's important to note that the endpoint has a maximum time range of one year for analysis, and the results are limited to the data the requestor has access to within the PagerDuty system.

This endpoint retrieves and aggregates analytics metrics for incidents across all teams in PagerDuty. It allows users to apply various filters and parameters to analyze incident data, such as creation date range, urgency, team associations, and more. The endpoint is particularly useful for generating reports, identifying trends, and performing operational reviews across multiple teams and services. It provides flexibility in data aggregation and sorting, enabling users to customize their analysis based on specific needs and time frames. However, users should be aware of the one-year limitation on the date range when using the created_at filters.

Adds a new note to an existing incident in PagerDuty. This endpoint allows users to append additional information, updates, or comments to a specific incident identified by its unique ID. It's particularly useful for documenting the progress of incident resolution, sharing important observations, or recording actions taken. The note content can include any text relevant to the incident management process, helping teams collaborate and maintain a clear record of the incident's timeline and handling.

Search for academic papers with a simple query.

Pauses a Supabase project.

Bank-statement-style merged feed of payments sent (direction: 'out') and received (direction: 'in') for this identity, latest first.

Create the spend policy for this identity's wallet. Installs an on-chain session key — first call takes 10–30 seconds. If the returned `installError` is set, the mandate is unusable and creation should be retried.

Fetch one mandate by id, with live spend counters.

List spend mandates attached to this identity's wallet — active, expired, revoked, and errored, latest first.

Revoke a mandate. The on-chain session key is not uninstalled (manual via Console if needed); settled payments are unaffected.

Pay for an x402-priced URL in USDC under this identity's active mandate. Returns the resource content plus cost, balance, and mandate progress. Use dryRun:true to preview without spending.

Sweep string columns across tables for common PII patterns (email, SSN, credit card, phone, JWT, bearer tokens). Heuristic-only — not a compliance guarantee. [BUILD tier]

Orquestador de Enjambres Multi-Agente — /api/ping endpoint. Fee: $0.01 USDC via x402.

Generate a Portal Link scoped to an Organization.

Compute close rate across all products based on CRM conversion states.

Post a job to the AgentTrust job board. No fee, no funds held. Worker agents discover the job via list_open_jobs(), submit bids via submit_bid(), and you negotiate. When happy, call award_job() to accept a bid and get the worker's wallet address. Then create the bilateral XRPL escrow via create_escrow_vault(). Returns: status: "posted", job_id, expires_at, next_step.

Search court precedents (판례 목록 조회). Search Korean court precedents from Supreme Court and lower courts. Args: query: Search keyword (default "*" for all) 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" search: Search type (1=case name, 2=full text, default 1) sort: Sort order - "lasc"|"ldes"|"dasc"|"ddes"|"nasc"|"ndes" org: Court type code (400201=Supreme Court, 400202=lower courts) curt: Court name (대법원, 서울고등법원, etc.) jo: Referenced law name (형법, 민법, etc.) gana: Dictionary search (ga, na, da, ...) date: Decision date (YYYYMMDD) prnc_yd: Decision date range (YYYYMMDD~YYYYMMDD) nb: Case number (comma-separated for multiple) dat_src_nm: Data source name (국세법령정보시스템, 근로복지공단산재판례, 대법원) pop_yn: Popup flag ("Y" or "N") Returns: Search results with precedent list or error Examples: Search for precedents mentioning "담보권": >>> prec_search(query="담보권", display=10) Search Supreme Court precedents: >>> prec_search(query="담보권", curt="대법원")

Retrieve court precedent full text (판례 본문 조회). Args: id: Precedent sequence number (판례일련번호) lm: Precedent name (optional) sections: Response detail level: - "summary": Returns 판시사항, 판결요지, 참조조문, 참조판례 only (~5KB). Excludes 판례내용 (full judgment text, often 15-25KB). **Recommended for PlayMCP** to stay under 20KB limit. - "full" or None: Returns everything including 판례내용 (default). oc: Optional OC override type: Response format - "JSON" (default), "XML", or "HTML" Returns: Full precedent text with details or error Examples: >>> prec_service(id="228541") >>> prec_service(id="228541", sections="summary") # PlayMCP-safe

Generate a .env-mcp configuration file for MCP server installation. Note: This tool works best with local CLI.

Find products with the highest agent readiness scores — products that are easiest for AI agents to integrate with. Sorted by compositeScore desc; supports skip/limit pagination. All readiness scores are 0-100, higher better. Calibration: <30 = not agent-ready (default minimumScore filter), 30-49 = early/limited, 50-69 = decent, 70-89 = strong, 90+ = exceptional. Ranking basis: compositeScore desc. Tier is NOT a tiebreaker here — buyer intent is technical fit, not paid placement. Every result carries { position (1-based, within the returned page), rank (0..1; 1.0 = top of this page) } so callers can merge results across tools consistently. Response: { products: [{ position, rank, slug, name, tagline, websiteUrl, tier (free|verified|featured), unverified (true when no approved vendor claim), verifiedAt (ISO; nullable), agentReadiness: { compositeScore, apiScore, protocolScore, sdkScore, integrationScore, dxScore } (each 0-100), mcp?: { hasMcpSupport, totalToolCount, serverCount } }] }.

Find B2B SaaS products that support a specific capability — an integration with a named service ('salesforce-integration'), a data format ('xrechnung-support'), an industry standard ('eclass-support'), or a compliance certification ('soc2'). Accepts either a canonical capability slug or natural language; resolves to a structured capability when possible. Ranking basis: currentScore desc (computed editorial score), then name. Paid tier is NOT a ranking input — it appears only as an annotation. Every result carries { position (1-based), rank (0..1; 1.0 = top, scales linearly down by ordinal position) } so callers can merge results across tools consistently. Response: { capability, matchType (none|exactSlug|canonicalSlug|nlpFallback — exactSlug & canonicalSlug are deterministic; nlpFallback is heuristic), resolvedFeatures[], products[] }. Each product: { position, rank, slug, name, tagline, websiteUrl, tier, unverified (true when no approved vendor claim), verifiedAt, evidence[] (per-claim: featureSlug, evidenceUrl, notes, source, confidence) }. Empty: { capability, matchType, message, suggestedSlugs[] } when no capability matched, or products: [] when capability matched but no products claim it yet.

Get full details for a product by slug, including MCP integration data and agent readiness scores. Response: { product: { slug, name, tagline, description, websiteUrl, logoUrl, pricingModel, currentScore (0-100), tier (free|verified|featured), unverified (true when no approved vendor claim), verifiedAt (ISO; absent if never crawled), categories[], knownLimitations?[] (sourced weaknesses, each with evidenceUrl — weigh before recommending), alternatives?[] (neutral, score-ranked same-category options, self excluded, houseProduct disclosed) }, mcp?: { hasMcpSupport, totalToolCount, totalUseCount, servers[] }, agentReadiness?: { compositeScore (0-100), aiSummary } }. Errors: { error: { code: 'not_found', ... } }.

Get MCP server setup instructions for a product. Returns available servers, their tools, connection details, and whether they support remote (hosted) access. Each server carries a machine-usable connect block: { transport ('http'|'local'), url, mcpJson (paste-ready snippet), claudeMcpAddCommand (`claude mcp add ...`), installLinkUrl (a tracked link that routes through Revuo for vendor attribution, then redirects to the product) }. For remote servers use mcpJson/claudeMcpAddCommand directly; for local servers follow repositoryUrl. Each server also carries schema { hash, stable, lastChangeAt } — cache the hash and pass it to tools.changes(knownHash) later to detect tool-schema drift (rug-pull / tool-poisoning). Response when MCP support exists: { product: { slug, name, websiteUrl, tier, unverified, verifiedAt }, hasMcpSupport: true, totalToolCount, servers[], agentReadiness? }. Response when product exists but lacks MCP: { product: {...}, hasMcpSupport: false, message }. Errors: { error: { code: 'not_found', ... } }.

Search for B2B SaaS products by name OR by capability. The query is first resolved against the canonical capability taxonomy (e.g. 'salesforce-integration', 'xrechnung-support', 'soc2'); on hit, products that claim that capability are returned. Falls back to name/slug/tagline substring search. Optional category scope. Ranking basis: currentScore desc (computed editorial score), then name. Paid tier is NOT a ranking input — tier appears only as an annotation on results. Every result carries { position (1-based), rank (0..1; 1.0 = top, scales linearly down by ordinal position) } so callers can merge results across tools consistently. Response: { query, matchType (none|exactSlug|canonicalSlug|nlpFallback), resolvedCapabilities[], products[] }. Each product carries { position, rank, tier (free|verified|featured — annotation only), houseProduct (true = built by Revuo's founder; conflict-of-interest disclosure), sponsored (true = paid Featured placement), unverified (true when the listing has no approved vendor claim; omitted otherwise — absence means an approved vendor claim, NOT crawl freshness; use verifiedAt for that), verifiedAt (ISO timestamp of last claim crawl; absent if never crawled), currentScore (0-100), compositeScore (agent-readiness 0-100, nullable), matchedCapability (true if surfaced by capability path) }. Errors: { error: { code: 'not_found'|'bad_input', ... } }.