"A personal assistant tool for managing schedules, notes, projects, and emails" matching MCP servers:

github-projects-mcp

MCP router that fronts your other MCP servers behind a few small generic tools, so their tool definitions stay out of the context window and are discovered on demand.

22 consolidated MCP tools for email, calendar, contacts, folders, rules, categories, and settings with safety controls (dry-run preview, rate limiting, recipient allowlists) and MCP annotations on every tool. Works with personal Outlook.com and work/school Microsoft 365 accounts.

Answers upgrade questions from a package's own changelog, listing breaking changes, deprecations, security fixes, and raised requirements between two versions, retrieving notes for a single version, and searching changelog entries for specific APIs or options.

Enables Claude Desktop to search, read, list, create, update, move, and delete notes from iCloud Notes on macOS.

End-to-end-encrypted markdown notes that double as agent memory: on-device semantic search (no API key), scoped and revocable agent keys, a hosted connector for Claude.ai and ChatGPT, and a self-hostable relay that stores ciphertext only.

Ask Claude, Codex or another AI assistant about your Garmin training, and get a training dashboard, also inside the chat. Official Personal API, read-only, nothing to install.

Saves the user's exact words as immutable, SHA-256-hashed captures before anything else, then derives events, entities, context cards, and causal hypotheses — every fact traceable to its verbatim source. Local-first personal memory for Claude Code, Codex, and any MCP client.

add sticky notes

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the results. Free AI moderation. Uses an organization API token from askone.org

Audits MCP tool descriptions for quality and reliability, scoring them 0-100, detecting smells, and providing rewritten versions for better agent accuracy.

Enables security operations workflows by providing tools for CVSS 3.1 scoring, IOC extraction and defanging, email header triage, hash and JWT decoding, timestamp conversion, layered decoding, and CISA KEV lookups.

Provides read-only network engineering analysis by parsing configs and logs to explain config changes, check CIS/PCI compliance, diagnose 802.1X issues, find embedded certificates, infer topology, and assess proposed changes before pushing them.

Graph-based tool retrieval for LLM agents. Builds a tool graph from OpenAPI/MCP specs and retrieves multi-step workflows via hybrid search (BM25 + graph traversal + embedding), recovering accuracy from 12% to 82% with 79% fewer tokens. Also works as an MCP Proxy to aggregate multiple servers behind 3 meta-tools.

Garmin Connect for Claude and any MCP client, on Garmin's official Personal API. Read-only access to sleep, HRV, Body Battery, stress, heart rate, activities and weight with a revocable key, no password or scraping.

Enables AI assistants to query Garmin training and recovery data—including activities, laps, strength sets, sleep, HRV, stress, and Body Battery—through the official read-only Garmin Connect Personal API. It also enables generating training dashboards and reviewing workouts, recovery, and readiness inside the chat.

Anonymous message board for AI agents over MCP. Read, search and leave short notes between autonomous agents with board_read, board_write and board_wait — no account required.

Enables AI agents to search, filter, and monitor curated AI model API free credits and low-cost token promotions through eight tools, four resources, and three prompts — including finding deals expiring soon, checking eligibility and blocked conditions, and producing daily briefs.

Personal Finance AI - MCP server providing AI-powered tools and automation by MEOK AI Labs

Protects AI agents from bad tool outputs, schema mismatches, and tool poisoning by validating, sanitizing, and scoring reliability of tool responses.

MCP server that detects and guards against tool poisoning and prompt injection attacks in tool descriptions and schemas. It provides risk scoring, pattern detection, safe rewriting, and audit reports with zero external API cost.

Cross-chain cryptocurrency swaps via Chainflip. Get quotes, execute swaps, and track progress. No API key required to get started.

Lets a human review what an AI agent is about to post to a chat tool (Slack first) before it is sent. Renders the draft, destination and warnings (@here/@channel, unresolved mentions, format issues) in a neutral local HTML preview; never sends anything.

A minimal, free MCP server in Python — persistent notes for AI assistants (create/list/search), local JSON storage. MIT-licensed starter built on the official mcp SDK.

Enables scoring the WHO-5 Well-Being Index from five answers, returning a 0–100 score and a low, reduced, or normal band without providing a diagnosis.

Provides agents with real Linux VMs to run commands, manage files, expose ports, and track costs, all through an ephemeral sandbox service.

Use Codex as a subagent inside Claude Code: async dispatch into a long-lived codex app-server, results pushed back into the Claude session automatically, steer/interrupt mid-task, and Codex's built-in code review.

Gives LLM agents spatial awareness inside Autodesk Maya, enabling scene inspection and measurement, aesthetic and engineering audits, camera planning, checkpoint/rollback safety, asset import, and viewport or render previews. Agents can also execute arbitrary Python in Maya to build and verify 3D scenes against engineering rules instead of writing blind.

Enables engineers to estimate LLM costs, check GPU VRAM fit, audit MCP configs for security risks, and analyze network device config changes and compliance—all locally, with no account or telemetry.

Odds are, most of what you want to build is already open source. Tell your AI agent what you're making, and it finds it: which repos to use as they are, which to adapt, and what's left for you to write. Every repo it names is real, licensed for your use or flagged, and checked live.