agentsclimarketplace
Sign in

Mcp bridge

Skill Harzva/deepseek-cli/skills/mcp-bridge

DeepSeek-first API CLI and Agent Skills toolkit with multi-provider fallbackFrom the repository description

Install
npx -y skills add Harzva/deepseek-cli --skill mcp-bridge

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.0 KB, 223 tokens by cl100k_base, as published. Nobody here has run it

MCP Bridge Skill

Use this skill when an agent needs to understand how Provider API CLI commands fit with Model Context Protocol (MCP). MCP is not a model-generation provider. It is an agent integration protocol for exposing tools, resources, and prompts to compatible AI applications.

When to use

  • The user asks how to expose provider-api commands to an MCP-capable agent.
  • The user needs a stable bridge between CLI commands and agent tools.
  • The user wants tool/resource/prompt vocabulary, not another chat-completions endpoint.

Safe pattern

  1. MCP server exposes a tool such as provider_api_chat.
  2. The MCP tool invokes deepseek, openai-api, gemini-api, or another CLI with --json.
  3. The CLI returns stdout JSON.
  4. The MCP server returns the result to the agent.
  5. Harness owns approvals, logs, retries, and tool execution.

Do not

  • Treat MCP as a replacement for Provider API calls.
  • Put API keys in prompts or tool descriptions.
  • Let the CLI execute arbitrary shell tools.

What ships with it: 3 files

389 B alongside SKILL.md

Gives 0 of the 12 instructions most mcp tooling skills give in 223 tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07

  • Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
  • Test servers using MCP Inspectorin 61 of 638, across 19 files
  • Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
  • Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
  • Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
  • Define structured output schemas where possiblein 50 of 638, across 8 files
  • Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
  • Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • Load framework documentation using WebFetchin 45 of 638, across 3 files
  • Verify each evaluation answer independentlyin 45 of 638, across 3 files
  • Implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 27 of 638, across 9 files

Said here and by no other author read

  • Expose provider-api commands as MCP tools
  • Invoke CLI commands with JSON output
  • Return stdout JSON to the MCP server
  • Let the harness own approvals, logs, and retries

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,764. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.