MCP Servers

Taisly Agent Kit MCP server for AI agent social media video publishing. Discover connected accounts, validate videos, publish or schedule posts to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook through Taisly. Install: npx -y @taisly/agent mcp. Requires a Taisly API key and connected accounts.

🎖️ - Web tools for AI agents through the Sofya API. Search the web for full page content instead of snippets, fetch URLs as clean markdown (including PDFs), extract structured data from a page with a prompt, and run multi-source deep research that returns a cited report.

🎖️ - Official Publora MCP server — schedule and publish posts across 10 social platforms (Twitter/X, LinkedIn, Instagram, Threads, TikTok, YouTube, Facebook, Bluesky, Mastodon, Telegram) from Claude, Cursor, or any MCP client. 18 tools for cross-platform posting, scheduling, media upload, and LinkedIn analytics. Hosted at mcp.publora.com.

Run a Shopstr / NOSTR marketplace storefront from an agent: create and update stalls and products in both the NIP-15 dialect (kind 30017/30018) and the Shopstr-modern dialect (kind 30019 shop + kind 30402 NIP-99 listings), including the Shopstr cache POST that makes cards actually render. 7 tools. npx -y marketplace-mcp.

Schedule, manage, generate, and analyze social posts across 11 networks (Instagram, TikTok, X, LinkedIn, YouTube, Facebook, Pinterest, Threads, Bluesky, Mastodon, Telegram) — 13 tools for scheduling, media upload, AI caption generation, best-times, analytics, listening, and comments. npx -y kadenzo-mcp.

Multi-account X (Twitter) automation with no X API key: it drives a real Chrome session using your own cookies. 33 tools for posting, replies, keyword search, engagement, single-tweet reads that return images as MCP content, per-account personas, proxy pools, and a persistent scheduled-action queue. Draft-approval mode is on by default, so write tools return a draft and nothing goes live until you call approvedraft. Listed on the official MCP Registry. Install: pip install x-use-mcp, then x-use

Control Instagram from Claude: publish photos, reels, and carousels, read account insights, manage comments, and reply to DMs. 14 tools via the Instagram Login API. One-click free Render deploy for Claude Web and mobile.

Post for Me MCP server with 27 typed tools to publish, schedule, edit, delete and analyze social posts across 9 platforms (Instagram, Facebook, TikTok, YouTube, X, LinkedIn, Pinterest, Bluesky, Threads), plus a postformeraw escape hatch and a readonly safety mode.

TikTok creator toolkit MCP — download videos without watermark, get curated 15-hashtag sets across 15 niches with strategy tips, look up best posting times for 12 countries, and generate viral hook formulas across 8 categories. No API keys, no signup, free. Install: npx -y tiktapdown-mcp. Companion to tiktapdown.com.

LinkedIn for AI assistants over an authenticated browser session — profiles, people/job/company search, feed, messaging, and gated writes (connect, message, post, react, comment) returned as structured JSON, with built-in rate limiting. npx -y linkedin-mcp-tools.

Local-first TikTok Content Posting API MCP and CLI for agents, with OAuth readiness checks, dry-run publish flows and live uploads only when explicitly enabled.

🎖️ - Check the reputation of an AI microservice or public API before calling it, and submit ratings afterward — from a free, open trust registry (no account or API key). Scores combine Bayesian reputation and EigenTrust, strengthened by cryptographically signed service receipts and a Merkle audit trail. Install: npx -y @trustscoreagent/mcp-server.

Post-quantum readiness for AI coding agents: scan code for quantum-vulnerable cryptography (RSA/ECDH/ECDSA/DH), explain the harvest-now-decrypt-later exposure, get NIST ML-KEM/ML-DSA/SLH-DSA (and hybrid) migration guidance, verify fixes, and check dependencies. Content-based/advisory tools only. Run local (npx @quantakrypto/mcp) or the hosted OAuth endpoint at mcp.quantakrypto.com.

Find MCP servers by natural-language task and get advisory trust screens (checktooltrust, assessserver) before you connect. The directory client for mcpindex.ai; advisory, not a safety verdict.

Domain security & privacy checker: 17 live checks (SPF, DMARC, DKIM, DNSSEC, TLS, CAA, security headers) scored 0-100 with remediation. Local-first, zero telemetry. In the official MCP Registry as com.oksigenia/checker-mcp; npm @oksigenia/checker-mcp.

Check whether a recruiter or job offer is a scam before you reply. Extracts entities (company, links, email, phone, wallets) from a pasted message and cross-checks company registration, domain age, look-alike/typosquat domains, phishing & malware blocklists, email deliverability, crypto-scam databases, and Internet Archive history — free OSINT, no API keys.

Pre-install trust layer for MCP servers, AI skills, and npm packages. Scores any repo or package across 15 signals (incl. OSV/KEV/EPSS vulnerability intelligence) with safety scanning for prompt injection, credential theft, and supply-chain risk; the autogate tool returns a go/no-go install decision. Listed in the official MCP Registry as io.mcpskills/server. npm: @mcpskillsio/server. https://mcpskills.io

Injects a live, reversible MCP server into a running Express / FastAPI / Next.js app — reads safe by default, writes gated behind human confirmation. The same engine also proves deploys and PRs (apocalypse / review).

Local credential approval and execution gateway for AI coding agents. Agents receive typed handles instead of raw API tokens, SSH keys, and cloud credentials; one-time approvals bind the credential, command, arguments, working directory, environment bindings, and target. Injects credentials only into the approved child process, sanitizes output, and records a local audit trail. Install with npm install -g @s-gw/s-gw.

Policy-as-code gate for MCP. A fail-closed proxy that denies risky tool calls before they run, produces offline-verifiable evidence bundles of what executed, and enforces IPv4/TCP egress in-kernel via eBPF/LSM and Landlock on Linux. Deterministic and offline-first.

Static security scanner and MCP server for MCP servers and AI agent tools. Detects secrets, shell execution, risky tool descriptions, environment access, and prompt-injection phrases. mcp-shield-server

Administer Keycloak through its Admin REST API — users, roles, clients, groups, identity providers, federation and events. Safe by default: read-only mode, realm allow-list, and confirmation for destructive actions. npx -y mcp-keycloak-admin

Microsoft Patch Tuesday triage from the official MSRC Security Update Guide. Monthly rollups, CVE/KB lookups, supersedence chains, product watchlists, and urgency-ranked results enriched with EPSS scores and the CISA KEV catalog. No API keys; also available as a free hosted remote endpoint. uvx patch-tuesday-mcp

AI-native HTTP security testing toolkit: 17 tools (send, intruder, race, chain, oob) with low-level control over HTTP/1.1 + HTTP/2 (raw framing, connection pinning).