← Back to Skills Marketplace
coros-open

coros-mcp

by coros-open · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
19
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install coros-mcp
Description
Install or refresh the COROS MCP connection inside OpenClaw through the global mcp.coros.com gateway, automatically pinning the session to the CN, EU, or US...
README (SKILL.md)

COROS MCP Login (Gateway)

Use this skill when the user wants one COROS MCP login skill that enters through mcp.coros.com and then uses the CN, EU, or US cluster selected by the gateway.

What to do

  1. Work from this skill directory, which contains scripts/coros_mcp_login.py.
  2. Prefer the resilient two-step flow when the browser might open on another machine, or when the CLI process may not stay alive the whole time:
python3 scripts/coros_mcp_login.py login-start
python3 scripts/coros_mcp_login.py login-finish
python3 scripts/coros_mcp_login.py apply-openclaw --server-name coros
  1. For a single-machine or quick refresh flow, use the one-shot helper:
python3 scripts/coros_mcp_login.py apply-openclaw --server-name coros
  1. The helper defaults to https://mcp.coros.com, reads the gateway-selected issuer from discovery, and then pins login, token refresh, MCP calls, and local cache files to that concrete regional issuer.

  2. If there is no local token cache yet, the helper will print a browser login link. Tell the user to open that link on their phone or computer browser and complete the COROS login there.

  3. If you used login-start, the helper saves the pending login locally on that same machine. After the user finishes the browser login, run login-finish on the original machine to complete the token save.

  4. To discover what this COROS MCP server currently supports, list tools dynamically. This command reuses a short-lived local cache first, so repeated requests stay fast:

python3 scripts/coros_mcp_login.py list-tools

Use --refresh only when you specifically want to force a live re-fetch from /mcp:

python3 scripts/coros_mcp_login.py list-tools --refresh
  1. Before calling an unfamiliar tool, inspect its schema:
python3 scripts/coros_mcp_login.py describe-tool --tool queryUserInfo
  1. To call a tool directly through this helper, pass a JSON object for the tool arguments:
python3 scripts/coros_mcp_login.py call-tool --tool queryUserInfo --arguments-json '{}'
  1. After the OpenClaw setup command succeeds, verify the saved MCP entry exists:
openclaw mcp show coros
  1. Tell the user plainly whether:
  • the saved COROS MCP entry was created or refreshed
  • a fresh login was needed or cached login was reused
  • the gateway resolved to CN, EU, or US if that matters for the request
  • the helper was able to initialize /mcp and discover/call the requested tool
  • any manual next step is still needed

Notes

  • Use apply-openclaw for setup or refresh. It will reuse saved login when possible and otherwise start the browser-based login flow.
  • Use login-start + login-finish when the browser may be on a different computer, or when the original terminal might be interrupted before the login completes.
  • Use login-status to check whether the original machine still has a saved pending login and to reprint the browser link.
  • Gateway mode keeps separate local state under ~/.coros-mcp-skill-gateway/\x3Cregion>/, so CN, EU, and US tokens do not overwrite each other.
  • If you must force a specific cluster, pass --issuer https://mcpcn.coros.com, --issuer https://mcpeu.coros.com, or --issuer https://mcpus.coros.com.
  • list-tools, describe-tool, and call-tool automatically reuse the local token cache and refresh the token before MCP requests when it is near expiry.
  • list-tools and describe-tool reuse a short-lived local tool catalog cache by default. Use --refresh when you want the latest live tool list immediately.
  • For natural-language requests, first run cached list-tools, choose the best matching tool from the current server response, inspect it with describe-tool only when the arguments are not obvious, then run call-tool.
  • If the selected tool needs required arguments that are still missing, ask the user only for those missing fields instead of dumping the full schema back to them.
  • If the user explicitly asks to keep using the old password-based flow, run the helper with --legacy and pass --username. The password will be prompted interactively.
  • Use logout only if the user explicitly asks to clear saved local login state.
  • Do not invent a second config path; always use the helper in this skill's scripts/ directory.
  • This is the hardened version. Token values are never printed to stdout. Error messages are sanitized to prevent sensitive data leakage.
Usage Guidance
Install only if you trust this publisher and want an agent to manage COROS MCP login plus potentially invoke COROS MCP tools under your account. Review what COROS tools are available before use, avoid legacy password login unless necessary, and use logout to clear cached local tokens when finished.
Capability Assessment
Purpose & Capability
The skill’s stated login/setup purpose is expanded in SKILL.md and scripts/coros_mcp_login.py to include listing, describing, and calling arbitrary COROS MCP tools with cached OAuth credentials.
Instruction Scope
The instructions tell agents to choose and call tools for natural-language requests, but there is no allowlist, per-tool confirmation requirement, or stated limit on what remote MCP tools may do.
Install Mechanism
Installation uses a local Python helper and the openclaw mcp set command; this is purpose-aligned for configuring an MCP server but writes authenticated configuration locally.
Credentials
The helper reads environment overrides, performs network calls to COROS gateway/regional hosts, and writes token, pending-login, and tool-cache files under ~/.coros-mcp-skill-gateway; these are expected for this integration but should be clearly understood.
Persistence & Privilege
It persists OAuth access and refresh tokens with 0600 permissions and can reuse them for future remote tool calls; logout exists, but the remote execution authority remains broad while cached credentials are present.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install coros-mcp
  3. After installation, invoke the skill by name or use /coros-mcp
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
coros-mcp v1.0.0 - Initial release of the COROS MCP login gateway skill for OpenClaw. - Enables seamless login and session pinning to CN, EU, or US clusters via the `mcp.coros.com` gateway. - Supports resilient two-step (login-start/login-finish) and one-shot (apply-openclaw) login flows. - Provides helper commands for listing tools, describing schemas, and calling MCP tools with automatic token caching and refresh. - Keeps per-region login state isolated, and hardens output to prevent sensitive data exposure.
Metadata
Slug coros-mcp
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is coros-mcp?

Install or refresh the COROS MCP connection inside OpenClaw through the global mcp.coros.com gateway, automatically pinning the session to the CN, EU, or US... It is an AI Agent Skill for Claude Code / OpenClaw, with 19 downloads so far.

How do I install coros-mcp?

Run "/install coros-mcp" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is coros-mcp free?

Yes, coros-mcp is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does coros-mcp support?

coros-mcp is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created coros-mcp?

It is built and maintained by coros-open (@coros-open); the current version is v1.0.0.

💬 Comments