AgentTeams is a runtime platform where multiple AI agents collaborate in shared Matrix rooms under the coordination of a manager. It is for human-supervised or enterprise workflows that need visible, auditable cooperation among agents running on different runtimes, with shared files and centralized traffic management.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add agentscope-ai/AgentTeams --skill mcp-server-managementgit clone --depth 1 https://github.com/agentscope-ai/AgentTeamsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/agentscope-ai/agentteams/mcp-server-management)<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/mcp-server-management"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/mcp-server-management/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/agentscope-ai/agentteams/mcp-server-management"><img src="https://agentmods.dev/badge/skills/agentscope-ai/agentteams/mcp-server-management.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00046 | $0.00524 |
| Opus 5 | $0.00023 | $0.00262 |
| Sonnet 5 | $0.00009 | $0.00105 |
| Haiku 4.5 | $0.00005 | $0.00052 |
Grade A, and why
mcp-server-management scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- 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
httpandssetransport —stdioservers cannot be proxied through the gateway
Operation Reference
Read the relevant doc before executing. Do not load all of them.
| Situation | Read |
|---|---|
| Create/update an MCP server or rotate credentials | references/create-update-server.md |
| Generate YAML for a custom API integration | references/custom-yaml-guide.md |
| List, inspect, delete servers, or manage consumer access manually | references/api-commands.md |
| Proxy an existing MCP server (SSE/HTTP) | references/setup-mcp-proxy.md |
| Need the GitHub MCP tool definitions | references/mcp-github.yaml |
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 33 lines · 46 tokens per session scan A e4e7f2be3347
mcp-server-management is a skill published in the GitHub repository agentscope-ai/AgentTeams (5,579 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 524 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. Use when asked to "ship", "deploy", "push to main", "create a PR", "merge and push", or "get it deployed". Proactively invoke this skill (do NOT push/PR directly) when the user says code is…
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Four modes: SCOPE EXPANSION (dream big), SELECTIVE EXPANSION (hold scope + cherry-pick expansions), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Use when…
design-review
Designer's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use…
plan-eng-review
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when…
autoplan
Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. Surfaces taste decisions (close approaches, borderline scope, codex disagreements) at a final approval gate. One command, fully reviewed plan out. Use when…
retro
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively…