Return raw credentials for a service when you need the API key directly. Includes automatic token refresh and rotation.
MIT
470,002 tools. Updated 2026-08-23 01:43
"Claris" matching MCP tools:
- Check credential validity and rate-limit status without making any external API calls. Queries only the Clavis vault and returns expiry, headroom, and last-used timestamp.MIT
- Securely call APIs with server-side credential injection, keeping API keys out of conversation. Prevents secret exposure and prompt-injection exfiltration.MIT
- Extract and store confirmed facts from conversations, using only final assistant responses and user verifications to build persistent memory.MIT
- View all services configured in Clavis for the authenticated developer. Identify which API keys and integrations are active.MIT
- Recall relevant memories ranked by relevance, recency, and importance for any query. Get the most pertinent information from stored memory.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceSecure credential management for AI agents — encrypted storage, auto-refresh, and rate limiting via a single MCP call. Supports OpenAI, Anthropic, Stripe, GitHub, Brave Search, Kalshi, Coinbase, plus generic API key and OAuth2 for any service.4113MIT
- AlicenseAqualityCmaintenanceClarity and memory for Claude. Persistent memory, intelligent context ranking, safety modes, and session checkpoints for Claude Desktop & Claude Code in a single install.20501MIT
Matching MCP Connectors
Prefeitura MG Montes Claros: Clearance Certificate (Debts), official-source lookup. Platform-hosted,
clariBI is an AI-powered business intelligence platform built for small and mid-sized SaaS, ecommerce, and operations teams. Instead of writing SQL or building dashboards manually, users ask questions in plain English ("what's our CAC by channel last quarter?") and the AI engine pulls the data from Stripe, HubSpot, Google Analytics, ad platforms, Jira, and 30+ other sources via the open Model Context Protocol. Dashboards generate themselves on source connect.
- Estimates token usage in the current session and sends a warning when context reaches 70% capacity.MIT
- Verify claims by cross-checking them against specified project files to detect hallucinated information. Uses a targeted file list, not a full repository scan.MIT
- Resume previous work by loading the latest or a specific checkpoint for a given project path.MIT
- Archive stale memories to maintain a lean, fast active memory. Specify project path and maximum age in days.MIT
- Build and query a file-to-purpose map for any project to understand what each file does. Index file intentions for instant codebase clarity.MIT
- Verify file protection status before editing. Request confirmation to proceed, ensuring safe changes without blocking.MIT
- Update a memory fact by ID with new text, confidence score, or status for persistent context management.MIT
- Clear project memories by specific category like decision, gotcha, or file, or delete all memories to reset context.MIT
- Reviews assistant responses to flag unverified claims and assumptions, ensuring clarity by prompting verification.MIT
- Analyze code diffs and get structured explanations of every change.MIT
- Retrieve all stored memories for your project, with optional filtering by category to quickly find relevant context.MIT
- Save a structured checkpoint of your current session state, including goal, progress, decisions, and next steps, to resume work later without losing context.MIT
- Track architectural decisions with dates, reasons, and affected files. Query decisions to find rationale and impact.MIT
- Export session data to the ./clarik-exports/ directory in JSON or Markdown format, ensuring it never saves to ~/Downloads.MIT