"Publishing deepseek-r1 LLM API as an MCP server and usage instructions" matching MCP servers:

Run DeepSeek as a real sub-agent inside Claude Code / Codex CLI — not just a single LLM call. DeepSeek gets its own 7-tool agent loop (Read/Write/Edit/Bash/Glob/Grep/NotebookEdit) inside a sandboxed workspace.

A local-first, multi-provider cost meter for LLM usage, exposed as MCP tools. Captures every call into a local SQLite ledger and lets any coding agent query spend, compare providers, and get recommendations — no cloud, no account. First-class support for Chinese providers (Qwen, DeepSeek) alongside Anthropic and OpenAI.

A Model Context Protocol (MCP) server that provides access to DeepSeek-R1's reasoning capabilities, allowing non-reasoning models to generate better responses with enhanced thinking.

MCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.

An MCP server that grants image recognition to text-only models like DeepSeek by forwarding images to vision models and returning text descriptions. Supports clipboard, pasted session images, and batch folder image recognition.

MCP server for DeepSeek AI models (Chat + Reasoner). Supports multi-turn sessions, model fallback with circuit breaker, function calling, thinking mode, JSON output, multimodal input, and cost tracking.

Delegates work from MCP clients (like Claude Code) to the Codex CLI, allowing spawning of autonomous Codex subagents for tasks.

Provides a SQLite-backed MCP server that records agent memory as history, enabling explicit consolidation, source checks, revisions, narrative versions, and accountable forgetting.

Enables integration of DeepSeek's language models with MCP-compatible applications, offering features like chat completion, custom model selection, and parameter control for enhancing language-based interactions.

This MCP server gives pure-text LLM agents vision capabilities by integrating the free GLM-4.6V-Flash visual model, enabling image, video, and file understanding through standard MCP tools.

Provides vision capabilities to text-only LLMs by acting as a cloud vision adapter layer, enabling image understanding and OCR text extraction through a single MCP tool.

MCP server that provides tools for evaluating LLM agent reliability, including adversarial task generation, automated LLM-as-judge assessment, and confidence statistics.

Deterministic SNAP eligibility logic, exposed as auditable Model Context Protocol tools. An AI agent can read, reason, and orchestrate, but the eligibility determination itself is made by versioned, tested, cited code that a caseworker, an auditor, or a court can inspect.

Enables AI coding agents like Claude Code or Codex to delegate tasks to a DeepSeek Harness subagent with its own context window, providing tools for task delegation, result waiting, continuation, and supervision with sandboxed execution.

Serves an LLM-maintained markdown wiki to agents over MCP, providing tools for querying and navigating wiki pages without direct filesystem access.

A local MCP gateway that unifies multiple LLM providers, API keys, routing, and multi-model discussions into a single tool surface.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

An MCP server for a plain-markdown LLM wiki vault with YAML frontmatter and Obsidian-style wiki-links, enabling headless full-text search, note reading, backlink discovery, and safe append/create-only writing with path traversal protection and an immutable raw/ directory.

Blind multi-model councils with anonymous LLM seats and direct 1:1 chat as a local MCP server. Enables asking one question to get independent answers from multiple model CLIs, then blind scoring and reveal.

Adds image understanding to text-only coding agents via two tools: describe_image for detailed descriptions and describe_ui for structured UI reports.