Taifost-Hermes MCP Server
Exposes two MCP tools for saving drafts and publishing content to Taifost Core, with secure authentication and idempotent behavior.
README
Taifost-Hermes
中文使用手册:docs/USER_GUIDE.zh-CN.md
实施架构与技术说明:
docs/IMPLEMENTATION_ARCHITECTURE.zh-CN.md
Hermes 角色配置与修改:
docs/ROLE_CONFIGURATION.zh-CN.md
The deliberately small integration boundary between Hermes Agent and Taifost Core. It exposes exactly two MCP tools:
taifost_save_drafttaifost_publish
The adapter computes the Markdown SHA-256 itself, sends a stable
Idempotency-Key, retries only transport/5xx failures, and never exposes the
Core bearer key to an LLM tool argument or tool result.
Configuration
Required environment variables:
TAIFOST_CORE_URL— Core origin, for examplehttp://127.0.0.1:2333TAIFOST_HERMES_API_KEY— the same secret as Core'sHERMES_API_KEY
Optional: TAIFOST_HTTP_TIMEOUT_SECONDS (default 20) and
TAIFOST_HTTP_RETRIES (default 3).
taifost-hermes-watchdog provides model-independent timeout notifications.
It scans the durable Kanban board, retries each configured delivery target,
falls back to later targets, and records successful notifications so one task
run is reported only once. The included user-level systemd timer checks every
five minutes. QQ is enabled now; add email to
TAIFOST_NOTIFICATION_TARGETS after Hermes email credentials are configured.
For the installed Hermes environment, add the block in
config/hermes-mcp.example.yaml to the
publisher profile only. The other profiles must not receive this MCP server.
The safe, secret-free role settings are recorded as config.overlay.yaml
beside each profile template. Merge those keys into the matching Hermes
profile; do not copy the orchestrator's QQ credentials into worker profiles.
Verification
PYTHONPATH=src python -m unittest discover -s tests -v
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.