MCP servers for documentation, knowledge bases, and content management. Connect Notion, Confluence, and other documentation platforms.
299 servers available
Query your product docs from AI tools. Source-cited answers from your indexed documentation.
Page-cited retrieval for embedded docs, datasheets, MISRA, CMSIS, and RTOS references.
Create your digital twin: a public page that answers from your own material, with citations.
@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
Self-hosted git-native knowledge base with an MCP endpoint your AI reads, writes and rewinds
First production Authority-MCP. W3C VC attested by Jassverband Schweiz.
Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
Connect to Atlassian Jira, Confluence, and Compass to search, create, and manage your work.
Remote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready evi
Remote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.
Remote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
Remote MCP for AI Studio Android release gate MCP, structured receipts, audit logs, and reviewer-rea
Remote MCP for AI waiver checks, exception approvals, expiry review, and audit receipts.
Remote MCP for Android CLI agent build gate, structured receipts, audit logs, and reviewer-ready evi
Remote MCP for Antigravity agent run receipt MCP, structured receipts, audit logs, and reviewer-read
A paid remote MCP for AI agent browser approval MCP, built to return verdicts, receipts, usage logs,
A paid remote MCP for developer endpoint scanner MCP, built to return verdicts, receipts, usage logs
A paid remote MCP for OpenAI Codex memory MCP, built to return verdicts, receipts, usage logs, and a
Remote MCP for C2PA disclosure policy MCP, structured receipts, audit logs, and reviewer-ready evide
Remote MCP for C2PA intake verifier MCP, structured receipts, audit logs, and reviewer-ready evidenc
A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,
A paid remote MCP for Context7 MCP docs, built to return verdicts, receipts, usage logs, and audit-r
Remote MCP for Copilot CLI switch gate MCP, structured receipts, audit logs, and reviewer-ready evid
A paid remote MCP for AI SDK data query MCP, built to return verdicts, receipts, usage logs, and aud
A paid remote MCP for AI SDK benchmark dashboard, built to return verdicts, receipts, usage logs, an
A paid remote MCP for AI SDK eval dashboard, built to return verdicts, receipts, usage logs, and aud
Remote MCP for Gemini Omni commercial rights receipt MCP, structured receipts, audit logs, and revie
Remote MCP for Gemini upgrade evals, prompt regressions, output diffs, and eval receipts.
Remote MCP for GenAI span mapping, provider normalization, dashboard schemas, and receipts.
A paid remote MCP for OpenAI Codex harness MCP, built to return verdicts, receipts, usage logs, and
Remote MCP for Kiro release readiness, evidence binders, signoff, and CI approval receipts.
Remote MCP for MCP tool deprecation receipt, structured receipts, audit logs, and reviewer-ready evi
A paid remote MCP for AI SDK MCP gateway registry, built to return verdicts, receipts, usage logs, a
Remote MCP for MCP consent scope receipt, structured receipts, audit logs, and reviewer-ready eviden
Remote MCP for tool license checks, vendor policy review, alternatives, and license receipts.
A paid remote MCP for AI agent browser MCP session, built to return verdicts, receipts, usage logs,
A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log
Remote MCP for Universal Cart merchant readiness MCP, structured receipts, audit logs, and reviewer-
Living knowledge graph for your repo: query with citations, remember/link facts, fact-check claims.
Up-to-date docs for AI. DEPRECATED: Use io.github.docfork/docfork instead.
Open-source all-in-one MCP-first customer platform: KB, Conversations, CRM, CMS, Outreach, Analytics
Read any public web page as a clean AIDocument (Markdown + structure) through Lyrenth.
md-log MCP: save/update/fetch markdown by path (stdio + remote HTTP, PAT auth).
Official Microsoft Learn MCP Server – real-time, trusted docs & code samples for AI and LLMs.
Search harness engineering, agentic AI patterns, architectures, governance and agent taxonomy.
The structured memory layer your AI is missing. Requires the free Wuniq desktop app.
Turn the LinkedIn posts you save into a knowledge base your assistant can search and cite.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Official MCP connector for Legalize: read and search its whole open corpus, at any point in time.
Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
Codebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.
Owned, portable working memory: a plain-files markdown brain any model can read and cite.
Generate PDF/DOCX/XLSX/PPTX from templates+JSON. Convert Office/HTML/MD to PDF. Universal templating
AI-native print-grade PDF generator. Markdown in, publisher-quality PDF out.
Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search.
Persistent knowledge system with OWL-RL reasoning and 22 MCP tools. Local-first.
Cited Q&A over your own notes, plus drift detection when a cited source changes. Local-first CLI.
Local-first personal finance MCP. Aggregates bank, brokerage, credit, and loan accounts via Plaid.…
FastMCP server for Obsidian wikilink suggestions from a pre-computed knowledge graph (graphify…
FastMCP server for surgical queries against a vault knowledge graph (NetworkX node-link JSON).…
FastMCP server for bidirectional sync between personal and team Obsidian vaults.
WhatsApp MCP. SQLCipher-encrypted, scrubber-CI-gated, draft-and-confirm sends, voice transcription.
Resolve documentation ownership, edit roots, checks, and human handoffs before an agent edits code.
Productivity framework for DevOps engineers using AI assistance (Claude Code) while working on PoCs
Codebase memory for AI agents: an AST index plus agent-written notes that self-stale.
Docstring quality vetting for Python -- enrichment, freshness, coverage, and presence checks
AI-native web scraper: scrape, crawl and map any site to clean markdown over stdio. MIT-licensed.
Standalone MCP server for Obsidian vaults — hybrid search, notes & files, memory, tasks, OAuth 2.1
Local RAG MCP for markdown documentation. Retrieval only; host synthesizes answers.
Local-first document management and semantic search for AI coding agents
Convert a document once, then get back only the passages that answer a question.
An MCP server that provides persistent memory and context management across sessions
Capture dev context on interrupt; replay it as a 30-second resume card. Git stash for your head.
Kotlin/Java library sources, public API and KDoc from the real Maven sources jar, for AI agents
Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.
Local Markdown/Obsidian knowledge substrate for MCP agents with governed memory and hybrid search.
Read-only access to deterministic engineering decisions stored in a local repository.
Publish, update, list, and delete Markdown pages on Booklet directly from your AI assistant.
MCP server for Architectural Decision Records: navigate, author, validate, link, and analyze them.
Share agent-generated Markdown as links — GitHub gists today, your own server tomorrow.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Israeli podcast & content marketplace MCP — 7 tools: studios, podcasts, glossary, industry report.
Token-auth Notion MCP: pages, databases, blocks, comments, files. Runs headless in CI and agents.
The canonical Python stdlib oracle for AI coding agents — always free, always MIT, token-frugal.
Share ordinary text files between concurrent agents without silently overwriting edits.
An MCP server that indexes and retrieves Plesk documentation.
Persistent, verified, cross-session memory for AI agents. 26 tools. SQLite + sync.
Local-first knowledge management with bi-directional LLM sync via Markdown files.
Open-source LLM knowledge base: team chat into a typed knowledge graph and auto-generated wiki.
Governance MCP server for agent-maintained knowledge bases (OKF): git-backed writes, search, lint.
Git-backed platform for skills, tools, and context for AI agents
Filesystem-first MCP for Obsidian — an LLM-maintained wiki inspired by Karpathy's LLM Wiki.
Convert .eml email exports to Markdown with YAML front matter
Laravel documentation aggregator: multi-version core docs, services, packages, learning paths.
Semantic search and pattern discovery for Obsidian and markdown vaults.
The project tracker for teams of humans and AI agents — in plain files. MCP server + CLI.
Persistent memory + causal root-cause analysis for AI coding agents. 123 MCP tools. EU, GDPR.
One shared memory for every AI you use, in plain Markdown files you own.
Pure-Go browser for AI: fetch pages, render JS without Chromium, return clean Markdown over MCP.
Two-layer memory MCP server for AI agents with 37 tools, RAG, graphs, wiki, auth
CometChat docs search + implementation bundles: add chat, voice, video & moderation to your app.
Semantic search + connection-discovery across your own Apple Notes (bridges, synthesis).
A committed markdown dev log and task graph that agents read and write over MCP.
Read, write, search, and surgically edit Obsidian notes, tags, and frontmatter via MCP.
Read-only semantic search MCP server for Obsidian vaults using local Ollama embeddings.
Agent-first local SEO quality, intent and opportunity engine with CLI and optional MCP server.
A searchable second brain for AI agents: ranked keyword and semantic search over your Markdown.
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
Up-to-date Docs for AI Agents.
Answer questions from documents too large to fit in context, reading only the sections you need.
Offline access to TwitterAPI.io docs for AI assistants. 52 endpoints, guides, pricing.
Offline access to TwitterAPI.io docs for AI assistants. 67 endpoints, 32 pages, 24 blog posts.
Fonto (FontoXML) documentation for AI tools. Converts DITA XML to Markdown on demand.
Convert Markdown into WhatsApp formatting: tables drawn to fit the phone's monospace width.
AI astronomy wiki with open agent peer-review. Vote on evidence, propose edits, earn reputation.
Catch spec drift before it catches you. Detect overlap, stale docs, and code drift.
Letterhead PDF as digital stationery: prints Markdown without overprinting header, footer, or logo.
A repository wiki of Markdown pages anchored to real code: read, search, and verified writes.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
Local-first LLM orchestration: memory, knowledge, state, routing, swarm, API discovery, plugins.
MCP server for AI agent read/write access to Obsidian vaults via EVC Team Relay.
Give AI agents access to your Obsidian vault via local files or Self-hosted LiveSync.
Local-first MCP server: Claude searches, asks & drafts from your Obsidian vault. 21 tools, no keys.
Private Agent memory and human-reviewed shared knowledge.
Serves the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.
Convert files and authorized public HTTPS pages to Markdown with secure job and billing guidance.
AI-powered reading triage MCP. 26 tools with a 24h burn timer. Read less, absorb more.
Manage your Plesk hosting server using AI assistants.
Search Obsidian vaults with hybrid full-text, fuzzy, semantic, and graph retrieval.
Self-hosted multi-user memory for AI agents: a human-readable Markdown wiki with per-fragment ACL.
One section in, one section out — on Markdown/GEML files, bad writes refused.
Read and write your Fresh Jots notes from Claude, Cursor, and any MCP client.
Local personal memory for agents as MCP tools — remember, recall, search, context, graph traversal.
MCP server for GroupDocs.Markdown — convert documents to Markdown via AI agents.
Convert DOCX/XLSX to Markdown — native chart-data extraction, optional VLM for figures
Governed MCP runtime for the Apple ecosystem, available on macOS with per-call approval.
Self-hosted AI-native knowledge workspace with hybrid search, GraphRAG, and MCP.
MCP server for Obsidian vaults - AI tools with consistent canonical context. Local-first.
AgentDocs (agentdocs.eu) MCP: read, search, write, comment, share & attach images to Markdown docs.
Convert web pages or HTML to clean Markdown for LLM context. Local, no external API calls.
Repository-native protocol and local MCP server for Work, Docs, History and durable project Memory.
Semantic search over IMAGIN.studio API documentation — CDN, API, integration guides, and more.
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.
Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
MCP server for codewiki.google: search repos, fetch wiki docs, ask questions
Living docs and MCP context for GitHub repos — conventions, gaps, and source-cited pages on merge.
Memory for AI agents — MLX (Apple Silicon) or CPU (Linux), sqlite-vec + BM25, zero cloud.
Fetch any web page as clean, AI-ready markdown with smart HTTP-to-browser escalation.
Read markdown with inlined images and index headings for agentic RAG workflows.
Section-level doc search for .md, .rst, .adoc, .ipynb, .html, .yaml, .json, and OpenAPI specs.
Fiber laser parts knowledge: laser sources, cutting/welding heads, CNC controls, alarm codes.
Memoria personal para Claude Code en notas Markdown; no carga el contexto a ciegas.
Query a verified document collection: passages that answer a question, with their source.
Deterministic, token-minimal agent memory: multi-hop [[wikilink]] recall with no LLM in the loop.
Graph context, semantic search, guarded edits, and reviewable Git for local Obsidian vaults.
Deliberation + live 5-model council divergence over the Omnarai multi-AI attributed corpus.
MCP server for searching and reading PmWiki pages with text queries and group filtering.
Cross-session memory for AI agents - knowledge graph, scoring, semantic search
Publish to self-hosted WordPress from AI agents: markdown, images, SEO, and Notion sync.
Local semantic search over your Obsidian vault - always fresh, never reindex.
Local-first personal knowledge base. Cited answers from your vault via vector + graph retrieval.
Memory for AI coding agents — markdown in your own git, not a vendor database. Apache-2.0.
MCP server for Bear notes — read, search, create, edit, tag, and manage notes via CloudKit
Drop-in fetch MCP: clean Markdown from any URL, with JS rendering and anti-bot.
Cited 'why was this decided?' answers for your repo and for React, Kubernetes, and Rust.
Read, edit, and analyze GeneXus 18 KB objects from Claude, Cursor, and AI agents.
Durable agent memory over a markdown vault: bitemporal facts, timelines, hybrid graph search.
Shared, peer-validated knowledge archive for AI agents — search, contribute, and validate via MCP
End-to-end encrypted access to a Standard Notes vault (protocol 004, local stdio only).
Local-first MCP memory server for persistent LLM knowledge with BM25 retrieval.
LuxAlgo Library — the encyclopedia of trading & technical analysis for AI agents. Free, keyless.
Collective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.
Compresses AI chat sessions into a typed knowledge graph. Local/offline via Ollama.
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
Local-first MCP server serving a project's business-domain knowledge to MCP-compatible agents.
Memory your agent can trust — every answer carries its source; when it doesn't know, it says so.
Curated knowledge for AI agents — 19K chunks, 121 skills, semantic search via MCP
Curated knowledge API for AI agents - skill packs, semantic search, validated patterns.
Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43 tools.
On-demand Obsidian vault access for AI coding assistants — 17 tools, 5 resources, 4 prompts.
MCP server for Bear notes — read, search, create, edit, tag, and manage notes via CloudKit
MCP server for Atlassian Bitbucket Data Center - interact with repositories and code
MCP server for Atlassian Confluence Data Center - access and manage content
MCP server for Atlassian Jira Data Center - search, view, and create issues
Local semantic search over Obsidian vaults via Smart Connections embeddings. Multi-vault, private.
Task management system for AI assistants with MCP protocol, templates, and bilingual support (TR/EN)
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK
Auto-document vibe coding sessions - collect, summarize, and publish
Web scraping, crawling, deep research & autonomous extraction — 29 MCP tools, clean Markdown/JSON
Markdown-first MCP server for Notion API with 8 composite tools and 39 actions.
Fetch any web page to clean Markdown with Litmus trust signals. No account or API key needed.
Search, read and edit Wiki.js pages, and manage its assets, users, groups and comments
Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.
Extract URLs from documentation, configuration and code, with their protocol and position.
Knowledge base for Claude Code with semantic search, feed intelligence, and teams
Local memory for coding agents. A rule with a runnable proof can refuse a wrong command.
Markdown MCP — search, extract sections, list headings, find code blocks.
Web scraping MCP — extract clean markdown, links, and metadata from any URL.
Auto, manual, or hybrid docs that never fall out of sync.
Access Obsidian vaults via Local REST API - read, search, and interact with notes
Search, read, and edit any MediaWiki wiki. Works with Wikipedia, Fandom, and more.
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
Long-term memory for AI agents — your Obsidian vault as searchable persistent memory.
Read and write a self-hosted TriliumNext knowledge base over its ETAPI.
Shared, project-aware memory for Claude Code, Codex, and other agents with human review.
Search and browse 2,900+ official GitLab documentation pages via MCP
Fetch web pages with SSRF protection. Returns clean, readable markdown from any URL.
Native macOS markdown preview with MCP server for Claude Code. Swift/SwiftUI, no Electron.
x402 MCP web parser: URLs to Markdown for agents. USDC on Base, Polygon, Arbitrum, Ethereum.
x402-gated LLM token compressor: strip filler, collapse JSON, densify prose. Paid in USDC.
x402-gated semantic vector cache for agent swarms: Redis-backed similarity lookup. Paid in USDC.
Confluence MCP — wraps the Confluence Cloud REST API v2 (OAuth)
Markdown utilities MCP.
Second brain en Obsidian: notas, conceptos como nodos, resurfacing y salud del grafo. En castellano.
Persistent session memory for Claude Code. Local SQLite, no LLMs, no network.
Offline, read-only MCP knowledge base for one Salesforce org's metadata, deps & impact.
MCP server for searching MCP protocol documentation
AI memory across Claude, ChatGPT, Gemini, and Cursor. Save, search, and recall context everywhere.
Generic markdown vault MCP with hybrid search
Read any web page as clean, ad-stripped Markdown past robots.txt and bot blocks, plus web search.
Jira & Confluence MCP: 24 tools for issues, sprints, comments, transitions & wiki. Run via npx.
Deterministic doc-drift detection: guard, score, explain, verify-claims and diagnose MCP tools.
Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.
Token-efficient MCP memory for Markdown vaults. Tiered search, GraphRAG, AI memories.
Rarefied Earth Groundwork MCP: company memory for AI agents. 14-day full-access trial, no card.
Publish Markdown to PostMD and get a shareable web page
MCP server giving AI agents persistent task memory across TickTick, Notion, GitHub, Linear & Beads
Japanese-web-native MCP server for low-impact, token-efficient web collection
Live docs MCP server. 598+ libraries, evidence-verified answers, code audit, snippets, dispatch.
JSDoc, README, changelog generation for AI agents
Markdown TOC, lint, format, stats for AI agents
CUDA-Q docs, API reference, and runnable examples for AI agents, pinned to your installed version.
Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown.
The open retrieval layer for AI agents — index code, docs, data. Search via MCP.
Git-backed markdown memory for AI agents; search hides superseded and archived notes.
Enables natural language schema queries — explore tables, keys, procedures, and get SQL help fast
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK
Local-first MCP sidecar for Markdown artifacts, review intents, and supervised knowledge growth.
Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.
Filesystem-direct Obsidian MCP server — search and edit your vault with low context-tax.
Notion MCP server — search, export, and import pages as markdown
Git-native project memory for AI assistants with enterprise-grade audit compliance
Local-first graph memory for AI assistants with SQLite, semantic search, and MCP tools.
Local read-only semantic search for Markdown vaults through MCP.
Temporal memory for AI with decay and reinforcement. Two-layer storage (JSONL + Markdown).
Open, source-cited knowledge base of Belgian insurance products: search, compare, verify, overlaps.
AI agent knowledge marketplace. Discover, purchase, and retrieve human expertise via x402 on Solana.
Podcast transcripts as clean Markdown with real speaker names — via the Spoken API.
The project brain for AI coding agents — memory, decisions, sprints, knowledge base via MCP.
AI debugging with 980+ verified fixes. Search the YanHui KB — never repeat a mistake.
Debug AI with shared KB. One bug fixed = everyone benefits. KB hit 4ms free, new analysis $0.05.
Save chat notes from Claude Desktop to your vault — MCP on Obsidian CLI. Keep what matters.
Publish AI-generated HTML & Markdown to a hosted, shareable URL via MCP.
Deterministic DOCX/PPTX/XLSX/PDF parser: track changes, comments, headers, footers, merged cells.
A validated Markdown memory vault your coding agent can recall, project by project.
Obsidian MCP server: semantic search, knowledge graph, and vault editing. No plugin required.
Verified knowledge base for AI agents — stop hallucinations with certified facts.
Agent-native knowledge OS on Markdown: typed graph, hybrid search, and compiler over MCP.
Shared long-term memory vault for AI agents with 20 MCP tools.
Personal knowledge graph every MCP client reads from and writes to. Portable across agents.
Find and monitor ocean shipments and containers, and create new tracking requests.
Deterministic ebook-to-markdown pipeline with MCP tools to browse, search, and read your books.
Vault-native, accountable memory for Claude Code and MCP clients. Markdown is ground truth.
AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.
AI-powered web scraping MCP. Distill pages to Markdown or extract structured data via JSON Schema.
Comprehensive PostgreSQL documentation and best practices, including ecosystem tools
Predict context rot, sign every agent write, tier reads. Markdown-native, 100% local.
Serve a folder of Markdown notes as an MCP server: hybrid search, reading, and sourced answers.
Filesystem-based MCP server for Obsidian vaults — read, search, and edit notes, no app required.
The document publishing layer for AI tools. Convert markdown to 6 destinations, 62 templates.
Open-source web scraper for AI agents with scrape, crawl, and map tools
Scrape, crawl, map & search the web. Open-source, self-hostable Rust crawler & search for AI agents.
Point-in-time, survivorship-free SEC EDGAR fundamentals + smart-money signals for AI agents.
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Local-first MCP server that exposes a Markdown vault through MCP.
Typed record store + hybrid search over MCP: deterministic lookups + semantic memory, per-customer.
Persistent memory for AI agents: Markdown entries, hybrid search, typed graph links
MCP server for Jira and Confluence — sprints, agile boards, attachments, versions, calendars.
Hosted MCP server for finding authoritative primary data sources and official portals.
Turns any web page into clean Markdown, page metadata and classified links for LLMs.
Git-native, review-gated knowledge base for LLM agents. Cited retrieval, audited writes.
Search your own Markdown notes, including languages written without spaces between words.
Research workspace for Zotero + Obsidian + NotebookLM. Search, ingest, sync, verify briefs.
Local QMD search and bounded index maintenance through a Streamable HTTP MCP server.
Markdown memory for AI agents. Files you can read, edit, grep, and commit. Not a database.
MCP Server that renders JavaScript SPA pages and extracts LLM-ready Markdown content
Local-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.
Three MCP tools: fetch_page, fetch_pages_batch, search_web. Ad-free Markdown for AI agents.
Shared, git-tracked working memory for AI agents on the same codebase.
Self-hostable team wiki; agents read & write it via MCP; Atlas turns your repo into a cited wiki.
Local-first AI PKM memory for coding conversations.
Enforce brand writing guidelines in Claude Code — PostToolUse hook + MCP server
Publish Markdown or HTML to a shareable link from your AI assistant. OAuth, no API keys.
Exam-scored knowledge brains your agent searches over MCP, plus a public list of their gaps.
Loads signed ALTWEB context capsules — refuses unsigned, tampered, or untrusted by default.