"How to invoke Claude code or API" matching MCP servers:

Your coding agent remembers how it solved past tasks and reuses it next time: trigger, steps, outcome, lessons. Hooks recall the right skill before a task; skills strengthen with confirmed use and unused ones decay. Local SQLite, no API key, nothing leaves your machine. 9 MCP tools, works with Claude Code, Codex and Cursor. Agent-written memory stays untrusted until you approve it.

Enables running multiple Claude prompts simultaneously in parallel with support for file contexts and output redirection to individual files.

Enables Claude Code to call Gemini models through an OpenAI-compatible API, providing tools for deep analysis, brainstorming, code review, and general queries using Gemini's capabilities.

Enables Claude Desktop and other AI tools to interact directly with Figma, allowing for powerful AI-assisted design capabilities through natural language commands.

Enables Codex to list and read saved Claude Code conversations, retrieve incremental context updates before replies, and optionally ask Claude text-only follow-up questions within a selected session without disrupting the workflow.

Enables Claude Code to retain cross-session memory of facts, decisions, and lessons with semantic search, while tracking user corrections as behavioral patterns and evolving self-improving frameworks over time. All processing runs locally through an MCP server and hooks, requiring no cloud service or API key.

Gives Claude Code persistent memory across sessions with semantic search, tracks and classifies user corrections to surface behavioral patterns, and evolves behavioral frameworks over time based on accumulated evidence. Runs entirely locally through 15 MCP tools and hooks, requiring no API key or cloud service.

Gives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections, and evolving behavioral frameworks that develop over time. Runs fully locally through Claude Code's hooks and 15 MCP tools, requiring no API key or cloud service.

Enables Claude Code to retain identity, memories, and behavioral frameworks across sessions — saving facts and decisions for later semantic search, detecting and classifying user corrections, and evolving learned frameworks over time. Everything runs locally through a SQLite-backed engine with 15 MCP tools plus hooks, requiring no cloud service or API key.

Cross-machine context sharing MCP server for Claude Code, enabling shared memory of decisions, patterns, and knowledge across multiple Claude Code instances on different machines.

Automatically converts OpenAPI/Swagger documents into MCP servers, enabling AI agents to call third-party REST APIs via the MCP protocol.

This MCP server gives Claude Code persistent cross-session memory with semantic search, automatic detection and tracking of user corrections as behavioral patterns, and reflective framework evolution that improves judgment over time. Everything runs locally through Claude Code's hooks and extension points, with no cloud, accounts, or API keys required.

MCP server that connects Claude Code to Substrate organizational memory, providing tools for searching, reading, querying, and writing memory, with automatic capture of conversation turns.

Enables Claude Code to retain persistent identity and cross-session memory through local semantic search over saved facts, decisions, and lessons, plus automatic detection and classification of user corrections to track behavioral patterns over time. It also reflects on accumulated behavioral signals to evolve and retire working frameworks, so responses adapt toward the user's judgment across sessions without cloud services or API keys.

Gives Claude Code persistent cross-session memory with semantic search, automatic detection and classification of user corrections into behavioral patterns, and self-evolving frameworks that refine judgment over time. Everything runs locally through hooks and MCP tools, with no cloud, API keys, or telemetry.

Enables interaction with the Sond Core API through the Model Context Protocol. Auto-generated from the OpenAPI specification at https://core-api-lb.sond.com/api-json to provide programmatic access to Sond's services.

Provides AI assistants with real-time web search, reasoning, and research capabilities through Perplexity's Agent API and Search API, enabling tools for search, conversational Q&A, deep research, and advanced reasoning.

Adds symbol-aware semantic search to coding agents like Codex CLI and Claude Code, enabling precise codebase context via natural language queries.

Enables reranking documents by relevance to a query through a Cohere-compatible API, so existing rerank code drops in with only a base_url change. Calls are pay-per-call in USDC via x402 or covered by a free daily tier, with no account, GPU, or model download needed.

Indexes codebases cut at function and class boundaries into Oracle AI Database 26ai, letting AI coding tools search code by name or meaning, trace callers, callees and change impact, read per-module wiki pages, and recall facts from earlier sessions. All of it is served over the Model Context Protocol with embeddings computed in-database, so no source code leaves the machine and no API key is required.