"Reading Local Project Files to Assist Development" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
Federated search of books and papers, BibTeX/RIS citations, open-access retrieval and reading.
Spin up a complete OpenCode development environment on any Linux box — one agent-driven workflow, six tools, zero secrets.
Local government intelligence for AI agents.
Spec-driven development MCP server: 8 phases, bi-directional traceability, 7 quality gates.
Read-only discovery and bounded access to a finite market briefing with evidence boundaries.
Argentine economic statistics sourced from official data (BCRA, INDEC, datos.gob.ar) as tools for AI agents: exchange rates, inflation, rates, reserves, activity, wages and trade. Search series, fetch history, projections with calibrated bands and the BCRA market consensus, weekly summary and release calendar. Independent project, not affiliated with any government agency. Free, attribution required.
Enterprise L402 data vending engine delivering real-time thermodynamic Bitcoin telemetry, Groth16 ZK-SNARK verification, Nostr P2P mesh consensus, and agent context grounding to autonomous AI swarms.
An MCP server that allows an agent to find the vendor that a network interface MAC address is registered under and other information about the block like it's registered country, the registry type it is in, how many addresses are in it's block and a link with more information. Stateless MCP 2026-07-28 version support only.
Dutch gross-to-net salary and social security (WW, WIA, IVA) calculation engine for 2026.
Douyin, Xiaohongshu, TikTok, YouTube, X links to text: transcript, screen text, viral breakdown
Provision an OpenCode workbench and MCP stack on any Linux box, local or over SSH.
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.
Cocktails you can make from bottles you already have, full recipes, and the best next bottle to add.
Threat intel for AI agents: IOCs, CVEs (EPSS/KEV), wallet sanctions and age, domain and URL checks.
Collective memory and evidence-backed trust for AI agents. Search reusable knowledge with search_memories, then inspect_memory to review provenance, reported outcomes and limitations before applying it. Discover public agents and inspect Trust Passports. Public reads require no account or credentials. This Streamable HTTP connector exposes public discovery and existing Candy sandbox tools; Candy participation uses a temporary bearer token and grants no canonical reputation or verified identity. Persistent Agent contributions use a separate authenticated connection described at https://remnant.dedale-bi.com/connect. Remote MCP: https://remnant.dedale-bi.com/mcp. Documentation: https://remnant.dedale-bi.com/connect. Examples: https://github.com/Dedale-Project/remnant-connect. Evidence and cryptographic integrity do not guarantee truth or safety. Bootstrap memories are operator-published, not independently validated.
Validate and clean CSV before import. Find duplicates, missing values and invalid dates with row-level reports. Apply only the cleanup you request; files are not retained. Run view_csv_demo free without a key. Custom CSV: EUR 9 for 100 operations, valid 90 days, no subscription. Setup: https://check.orvel.dev/docs/
Four tools to check, watch, diagnose and verify AI agents and MCP servers. Free, read-only.
Formgong is the fastest way for an AI coding assistant to give a website a working contact form, with no backend code. One MCP call creates the form, the next returns ready-to-paste HTML, React or Next.js code with the access key filled in, and submissions start arriving in email and Telegram right away. - Email and Telegram delivery on every plan, including Free. Telegram connects with one button and works in groups. - Signed JSON webhooks (HMAC-SHA256, up to 5 delivery attempts) with step-by-step recipes for Make, n8n, Zapier and KeyCRM. - Data stored in the EU; IP kept only as a hash; a standard Art. 28 DPA is part of the Terms. - Spam protection with no CAPTCHA puzzle and no cookies: honeypot, cookie-free checks, optional Cloudflare Turnstile. - Thank-you page, errors and auto-reply in the visitor's language (12 languages). - Lead reminders in Telegram for leads nobody has handled. - Projects for agencies: up to 100 client projects, view-only client invites, handover to the client. - Free: 300 submissions a month, unlimited forms. Pro $5/month, Business $15 (as of Oct 2026). - Read-only access to recent submissions is opt-in; IP addresses and user agents are never exposed. Tools: list_forms, create_form, get_form_snippet (html | react | next), list_recent_submissions. Auth: Authorization: Bearer <personal API token> from Formgong Dashboard → Account → API tokens. Endpoint: https://formgong.com/mcp (Streamable HTTP). Docs: https://formgong.com/en/docs/mcp/
Connect GlamAI.ai with Blog2Social to create, manage, schedule and publish AI-generated content across 25+ social media, blogging and community platforms. Publish text, links, images and videos, manage connected accounts, automate multi-network distribution and retrieve publishing results and social media insights through one secure MCP integration.
Audit MCP configs and skill files for over-broad scope and injection risk. 6 of 8 free.
