"Affinity Publisher" matching MCP servers:

Enables searching HAL and preparing, validating, and submitting publication deposits via SWORD, with dry-run validation and explicit submission control.

MCP server for publishing posts and retrieving metrics on social platforms like Telegram, with planned support for YouTube and Instagram.

Enables searching recent news coverage from 28 Chinese, Hong Kong, Taiwanese and overseas-Chinese publishers, with headline, publisher, URL, publication time, theme tags and average article tone, plus an audited publisher census and article metadata lookups.

A Python MCP server on Cloudflare implementing the stateless MCP 2026-07-28 protocol, enabling load-balanced and scalable tool execution without session affinity.

MCP server for biological protein design, folding, and affinity prediction using Refua tools, with optional support for ADMET, clinical simulation, preclinical planning, wet-lab automation, and more.

A FastMCP server backed by Postgres that demonstrates MCP tools, resources, and prompts, with a focus on session affinity and load balancing via HAProxy.

Enables searching Japanese scientific articles and journals on J-STAGE, with tools for article search, journal search, and volume listing, returning metadata and links to full text on publisher sites.

Enables an AI client to search Australian federal and South Australian government open data catalogues, inspect a dataset file's schema and sample rows, then run read-only SQL over the full file in a sandboxed DuckDB. Every answer carries the source URL, publisher and licence, with extra tools for ABN checksum validation and Australian financial-year dates.

MCP server that integrates affiliate networks with Claude and Codex, enabling natural language queries across publisher and advertiser-side data from multiple networks.

Enables Codex to access and extract approved publisher content, including article text, figures, PDFs, and supplementary information, through governed persistent browser sessions and challenge recovery.

Enables AI assistants to access Published NFT documentation, NFT collections, Flow blockchain info, pricing, and other literary marketplace data through MCP tools.

Enables querying and browsing educational resources from AMB Nostr relays — cross-content full-text search, passage retrieval with citations, filtering by publisher, subject, level or type, SKOS vocabulary lookup, calendar event search, and URL-to-form-prefill metadata extraction. It also supports signing and publishing Nostr events (including AMB educational resources) via NIP-46 remote signing, with stdio, HTTP and ContextVM transports.

Enables agents to discover feeds for a site, retrieve dated feed items as clean JSON, and perform keyless news searches across Google News and Bing News with deduplication and publisher attribution.

Enables AI agents to resolve places and statistical variables, then retrieve harmonised public statistics such as population, income, health, employment, and emissions with publisher provenance and child-place comparisons.

Enables looking up Chrome Web Store listing data — a single extension by its 32-character id, free-text search across extensions, and extensions attributed to a given publisher. Returns details such as name, rating, rating count, user count, version, last-updated date, category, and website.

Enables searching and exploring Spain's National Open Data Catalog, letting users find datasets by title or theme, list available themes, retrieve full dataset records with publisher, license and distribution details, and obtain catalog totals via the official SPARQL endpoint. It connects over Streamable HTTP, SSE, or local stdio using the public keyless datos.gob.es API.

Enables discovery and querying of public OpenBind structure-affinity datasets, experimental binding events, benchmark results, and live Fragalysis targets and observations through read-only REST endpoints without requiring an API key.

A flexible MCP server that enables users to fetch recommendations from the Taboola API using publisher credentials, supporting both local (STDIO) and remote (HTTP) deployment modes.