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 agentmods add skills/teamsparkai/mcpgraph/mcpgraphtoolkitnpx skills add TeamSparkAI/mcpGraph --skill mcpgraphtoolkitgit clone --depth 1 https://github.com/TeamSparkAI/mcpGraphWhat 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 | $0.00068 | $0.06930 |
| Opus 5 | $0.00034 | $0.03465 |
| Sonnet 5 | $0.00014 | $0.01386 |
| Haiku 4.5 | $0.00007 | $0.00693 |
Grade A, and why
mcpgraphtoolkit 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 2d 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 — 879 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Building mcpGraph Tools with mcpGraphToolkit
This skill teaches you how to use the mcpGraphToolkit MCP server to build, debug, test, run, and manage graph tools in an mcpGraph.
What is an mcpGraph
An mcpGraph is a declarative configuration that defines an MCP (Model Context Protocol) server and its tools, where those tools are implemented as directed graphs. We call those exported tools "graph tools". Each graph tool executes a sequence of nodes that can:
- Call other MCP tools (that are available to the mcpGraph)
- Transform data using JSONata expressions
- Make routing decisions using JSON Logic
When to use mcpGraph:
- You need to orchestrate multiple MCP tool calls in sequence
- You want to transform data between tool calls
- You need conditional routing based on data
- You need to compose complex workflows from simpler MCP tools
Using the mcpGraphToolkit
What you should do:
- ✅ DO use
listMcpServersandlistMcpServerToolsto discover available MCP servers and tools - ✅ DO use
getMcpServerToolto get MCP server tool details and schemas - ✅ DO use
addGraphToolto add graph tools to the mcpGraph (it handles file operations automatically) - ✅ DO use
updateGraphToolanddeleteGraphToolto manage graph tools - ✅ DO use
runGraphToolto run a graph tool or to test a graph tool before adding it - ✅ DO use
listGraphToolsandgetGraphToolto discover and examine existing graph tools, especially when considering creating a new graph tool
⚠️ CRITICAL: Use Only the Provided Tools to interact with an mcpGraph
DO NOT create, edit, or read configuration files directly. mcpGraphToolkit uses configuration files internally (such as graph configuration files and MCP server configuration files), but you should never attempt to create, edit, or read directly from these files. The toolkit tools provide all the functionality you need to understand and manipulate the state of the mcpGraph.
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.
- 2d ago First seen · 879 lines · 68 tokens per session scan A 7effa7c3230e
mcpgraphtoolkit is a skill published in the GitHub repository TeamSparkAI/mcpGraph (21 stars, last pushed 7mo ago), licensed MIT. It adds 68 tokens to every session and 6,930 once invoked, about $0.0003 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
mcporter
List, auth, and call MCP servers/tools from the terminal.
agent-messaging
Send and receive cryptographically signed messages between AI agents using the Agent Messaging Protocol (AMP). Use when the user asks to "send a message to an agent", "check agent inbox", "message another agent", "reply to a message", "notify an agent", or any inter-agent communication task.
📝 任务完成后归档
重要提醒: 每次完成复杂调试或开发任务后，主动执行此流程！ 将学到的经验归档为 skill，供以后参考。不要等用户提醒。.
oracle
Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).
agent-mode
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
agento11y-prod-setup
Sets up production evaluation and guardrails for a DEPLOYED AI agent in Grafana Agent Observability, grounded in the agent's own code and its real ingested traffic. The judgment layer on top of the agento11y skill: it reads the agent's source (system prompt, tools, entrypoint) AND samples its live traffic via gcx…