Skip to content
cccskills
FreePublished on GitHub

mcp-server-management

Configure external APIs and existing MCP tool servers through Higress AI Gateway. The skill covers YAML-based setup, credential updates, Worker access permissions, and connection checks before making tools available to the Workers that need them.

OriginalShow the original description

Use when admin asks to configure an MCP tool server (e.g., GitHub, weather API), rotate credentials, grant/revoke worker access to MCP tools, or add a custom API integration via YAML.

Works withGitHub
See how to install

Good for

  • Expose an external API as an MCP tool
  • Update credentials for a tool server
  • Grant or revoke Worker access to tools
  • Proxy an existing MCP server through the gateway

Files included (8)

  • SKILL.md2.7 KB
  • references/api-commands.md1.7 KB
  • references/create-update-server.md4.1 KB
  • references/custom-yaml-guide.md3.8 KB
  • references/mcp-github.yaml45.8 KB
  • references/setup-mcp-proxy.md3.2 KB
  • scripts/setup-mcp-proxy.sh14.7 KB
  • scripts/setup-mcp-server.sh19.6 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

MCP Server Management

MCP Servers expose REST APIs as tools on the Higress AI Gateway, or proxy existing MCP servers (SSE/StreamableHTTP). Use setup-mcp-server.sh to create/update from YAML templates, or setup-mcp-proxy.sh to proxy existing MCP servers. Built-in templates are at references/mcp-*.yaml.

Gotchas

  • Self-hosted Console in another container: set HIGRESS_CONSOLE_URL (or AGENTTEAMS_HIGRESS_CONSOLE_URL) to its reachable address. You can reuse HIGRESS_COOKIE_FILE or let the scripts log in with AGENTTEAMS_ADMIN_USER / AGENTTEAMS_ADMIN_PASSWORD. If Controller-local Worker credentials are unavailable, the scripts save your Worker MCP assignments through agt apply; wait for reconciliation and file-sync before verifying tools.
  • Cloud mode (AGENTTEAMS_RUNTIME=aliyun) does not support script-based MCP management — direct admin to the Alibaba Cloud AI Gateway console instead
  • Auth plugin takes ~10s to activate after server creation/update — always wait and verify with mcporter before notifying Workers
  • Always verify end-to-end before notifying Workers — call at least one tool via mcporter to confirm connectivity. Do not push broken tools
  • Never echo credentials in chat messages — credentials are stored only in Higress config, Workers access via gateway proxy
  • Consumer authorization is a REPLACE operation — when calling the API manually, include ALL consumers (manager + all workers), not just the new one
  • All YAML configs must use accessToken: "" as the credential key — the setup script substitutes the real value
  • Only notify relevant Workers — do not broadcast to all Workers, only those whose role/task needs the new tool
  • MCP Server SSE endpoint always returns 200 — auth is checked on POST /mcp/<name>/message, not on SSE connect
  • mcp-proxy only supports http and sse transport — stdio servers cannot be proxied through the gateway

Operation Reference

Read the relevant doc before executing. Do not load all of them.

SituationRead
Create/update an MCP server or rotate credentialsreferences/create-update-server.md
Generate YAML for a custom API integrationreferences/custom-yaml-guide.md
List, inspect, delete servers, or manage consumer access manuallyreferences/api-commands.md
Proxy an existing MCP server (SSE/HTTP)references/setup-mcp-proxy.md
Need the GitHub MCP tool definitionsreferences/mcp-github.yaml

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Find worker agents in Nacos that match a task, recommend candidates, and import the administrator's chosen worker. It also supports importing a specified nacos package URI, with worker name confirmation and direct reporting of installation failures.

  • Find a suitable worker for an unassigned task
  • Compare Nacos worker candidates before importing
  • Import a worker from a specified nacos package URI
agentscope-ai/AgentTeams5.8KUpdated Oct 17, 2026

Prepare an existing OpenClaw setup for import as an AgentTeams managed Worker. Analyze tool dependencies, adapt role instructions and scheduled jobs, and build a ZIP package containing the configuration and custom image requirements.

  • Moving standalone OpenClaw into AgentTeams
  • Reviewing required tool dependencies
  • Adapting role instructions for a Worker
agentscope-ai/AgentTeams5.8KUpdated Oct 17, 2026

Manage communication channels by identifying senders, maintaining trusted contacts, and setting the administrator's primary notification destination. It also covers first contact on a new channel and contacting the administrator across channels, with rules for handling unknown senders.

  • Identify who sent a message in a room
  • Add or remove trusted contacts
  • Configure the administrator's primary notification channel
agentscope-ai/AgentTeams5.8KUpdated Oct 17, 2026

coding-cli

FreeSummary

Prepare coding tasks for delegation to an authorized agent’s AI command-line tool. Set up and synchronize the workspace, write precise change requests, then review returned changes and run relevant checks before reporting completion.

  • Delegating code implementation or bug fixes to an AI CLI
  • Writing coding requests with clear acceptance criteria
  • Reviewing and testing changes returned by a CLI
agentscope-ai/AgentTeams5.8KUpdated Oct 17, 2026

Run AI coding command-line tools on behalf of worker agents using their prepared prompts and workspaces. Detect available tools, configure delegation, return results, and apply supported execution controls such as time budgets and permission settings.

  • Running coding tools for worker agents
  • Detecting and selecting available coding CLIs
  • Setting Qwen Code permissions and time budgets
agentscope-ai/AgentTeams5.8KUpdated Oct 17, 2026

communication

FreeSummary

Guide agent replies in Matrix chat rooms, including when to mention a coordinator, report completion, raise blockers, or answer questions. The rules limit repetitive acknowledgments and stop exchanges that add no new task, question, or decision.

  • Reporting task completion to a coordinator
  • Raising blockers or questions that need action
  • Reducing repetitive acknowledgments
agentscope-ai/AgentTeams5.8KUpdated Oct 17, 2026

See all skills by agentscope-ai

Report a problem with this skill