"Semantic code navigation tools for AI agents" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Enhanciar is an AI company brain for every team. It reads your Slack, Gmail, Google Drive, Notion, Confluence, Jira, Linear, Zendesk, GitHub code and databases, writes a wiki from them, and answers questions from any MCP client with a link to the source. Tools: query (cited answers), search_wiki, get_page, list_pages, get_graph, get_process_map, impact (what a code change touches), list_repos, list_skills, get_skill, propose_action and list_proposed_actions (tickets, Slack messages, Gmail drafts, Notion pages and calendar holds that a person approves first). Hosted service, bring your own AI key. Plans: Solo $24 a month, Team $100 a month for up to 10 people. Create an API key in Settings at https://enhanciar.in.
Engram is a persistent, long-term memory layer for AI agents and assistants. Claude, ChatGPT, Grok, Cursor and any MCP client share one memory, stored as plain markdown notes: your knowledge base, second brain and AI context in one place. No extraction step: the memory is the note itself, so you can read exactly what your AI remembers and fix it. Edit your memory in Obsidian (real-time sync), the web app, or on your phone. Hybrid keyword + semantic search (RAG over your notes) finds exact strings like error messages, config keys and IDs. Remote MCP server over Streamable HTTP with OAuth 2.1; notes encrypted at rest. Https://engram.page https://youtu.be/rwnPeZ-8Lqo?is=NI-N7BduydGAiZlF https://github.com/engram-app/Engram
Cloud or self-hosted knowledge for AI agents: hybrid search, reranking, GraphRAG, scoped MCP tools.
ESG knowledge base for AI agents: hybrid search, glossary, frameworks, industries, graph traversal.
Marcora is the context layer for go-to-market teams. Build your source of truth once: a Brand Foundation (positioning, brand voice, and writing style) plus a Reference Library of product docs, buyer personas, competitive analysis, and messaging. Claude, ChatGPT, and any AI tool that supports MCP connections read from it, so what you write stays on-brand and accurate.
Source-tiered retraction and citation judgments for DOIs; abstains when evidence is thin.
An AI clone of you that people can talk to. It answers from what you wrote and says it is an AI.
Governed organizational memory for AI, by EigenAtom. ChatGPT, Claude, Cursor and other agents save explicit memories to one shared store over MCP; AI only suggests labels, and the organization's deterministic policy decides who may read each memory, so recall returns only what the signed-in person may see. No admin bypass, audited changes, and memory content never reaches logs. Free 60-day trial, no credit card.
Deterministic AI agent microtools, no accounts/API keys. fetch_extract: 98% token cut. 47 tools.
Document to Markdown: convert Word, Excel, PowerPoint and PDF files to Markdown for an LLM.
Durable shared memory for AI agents: search, write and correct facts, with per-client policy.
Dated, verified API breakages for coding agents, plus a local scan for them in your existing code.
Read-only corpus catalogs and bounded observations with source dates and rights metadata.
Your own memory inside ChatGPT and Claude, with the source of every note.
Your personal library, readable by AI agents: durable snapshots, hybrid search, 46 MCP tools.
CVE, KEV, MITRE ATT&CK, CWE and detection graph for AI agents; every link names its source.
Cited deep research for agents. Estimate the cost, start research runs, read graded sources and ask grounded questions of a finished report. Every claim links to the passage it came from. Also lists and runs saved research workflows. Requires a Farside API key sent as an Authorization: Bearer header.
Everything your AI agents need to do their jobs, with a spending cap they can't go over.
15 pay-per-event data APIs for local-business and web intelligence: Google Maps, reviews, social and professional scrapers, RAG web browsing, France fuel prices, hotel rates, API change monitoring, local AI presence audits and monitoring, AEO checks, and AI brand visibility tracking.
Hybrid sparse-dense neural search with cross-encoder re-ranking and semantic retrieval over streamable HTTP.
Find explanations and worked examples in Ithy’s public article library, from SSD capacity to USB-C cables. Search titles and descriptions, then read relevant passages with source links and dates. No account or API key. Read-only; no new research or private data access. Articles are AI-assisted secondary sources—check important claims against original references. https://ithy.com/connect
Ask, search and review your Denser AI chatbots: knowledge base, chats, analytics and leads.
Discover MCP servers and packages, inspect their documented capabilities, endpoints, authentication requirements, provenance and observed readiness, and retrieve cited reference passages with document versions. Koskamo provides public discovery and reference tools alongside separately authorized contributor and owner workflows for server registration, listing maintenance, keys, issue reports and operation receipts. Tool discovery does not grant write authority: protected actions require the applicable account or owner key and documented confirmation. Live protocol observations and directory records are evidence of what was observed, not a guarantee that every connected service or tool works without its own credentials. Returned reference passages and third-party descriptions remain source material to review before citing or acting. Official connector repository: https://github.com/empline/koskamo-mcp. Support: support@koskamo.com.
AI Bible study you can actually check: Scripture, Hebrew and Greek, and the church fathers.
A second brain for your AI agent. Shared memory for your team's AI agents, plus public and private knowledge bases — works with ChatGPT, Claude, Cursor and any MCP client.
Search and fetch tools over the pages of pournasserian.com, Amir Pournasserian's personal website: his writing on MCP, AI agents and RAG, his experience, case studies and open-source projects. No authentication. Runs the open-source mcp-my-site.
Count tokens (o200k/cl100k), truncate to a budget, chunk text for RAG and estimate LLM cost.
The only News based AI MCP your agents will ever need — custom categories, global regions, and time-scoped results in one tool. We use multi-vector & sparse-hybrid search to search through thousands of articles across the world to find the exact news you're looking for.
Machine-exclusive web distillation MCP server for AI agents. Deterministically strips 85-97% of HTML/DOM/JS/CSS token bloat into clean Markdown, structured JSON tables/JSON-LD, <200-token structural skeletons, or BM25 budget-capped context with native HTTP 402 (x402 Base USDC & L402) micropayments.
One question, one checked answer: quote-verified answers from the web and ~45 structured sources.
Cited web evidence and fact checking for AI agents. $0.01 per call, no API key.
Cited news for AI agents from AI companies, VC firms, private companies and business podcasts.
Ask questions about Claude Code, Cursor, Codex and MCP — get answers grounded in their official docs, with citations. A hybrid RAG service that AI agents call through two MCP tools (or over REST). It indexes ~600 pages of official documentation, refreshes itself daily, and every design choice is backed by an experiment.
The right context at the right time, from the world's leading data providers. One API. 800+ tools.
jitprompt gives your agents just-in-time instructions. Upload your docs as they are, and your agent gets the right section over MCP at the moment it needs it, instead of 20k tokens of system prompt every turn.
Verified Texas business records for AI agents: entities, licenses, openings and enforcement history.
Fresh context for agents. Ask, search or follow stories. Each fact cites a Synorb Manifest.
Search Fragments — two tools for the queries an agent can't place, both built to decline rather than guess. resolve_fragment takes a half-remembered, cross-source query ("a musician who became famous for stopping performing") and returns a grounded answer, ranked web sources to confirm by eye, or an explicit no-resolution. verify_claim takes a specific factual assertion and returns supported, partially_supported, insufficient_evidence, or unsupported, with cited evidence and a stated_limits field that is always present. There is no confidence score — insufficient_evidence fires freely, and unsupported requires a source that explicitly contradicts, never mere absence of confirmation. Every verdict is decide-by-eye: "supported" means current web sources confirm it, not that the claim is true. Calibrated against 18 known claims before release. Free, no signup. Streamable HTTP (MCP 2025-11-25). Read-only.
Verify a company, figure or citation before you rely on it. Card or crypto; signed receipt.
Turn URLs, PDFs and DOCX into clean Markdown for agents, plus prompt-injection scanning
