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 arrase/ollama-agent --skill mcp-configuratorgit clone --depth 1 https://github.com/arrase/ollama-agentWrote 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/arrase/ollama-agent/mcp-configurator)<a href="https://agentmods.dev/skills/arrase/ollama-agent/mcp-configurator"><img src="https://agentmods.dev/badge/skills/arrase/ollama-agent/mcp-configurator/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/arrase/ollama-agent/mcp-configurator"><img src="https://agentmods.dev/badge/skills/arrase/ollama-agent/mcp-configurator.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 | $0.00043 | $0.01682 |
| Opus 5 | $0.00022 | $0.00841 |
| Sonnet 5 | $0.00009 | $0.00336 |
| Haiku 4.5 | $0.00004 | $0.00168 |
Grade A, and why
mcp-configurator 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 12d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Configurator
Model Context Protocol (MCP) connects ollama-agent to external tools, databases, and developer services. In ollama-agent, MCP servers can be attached globally to the main orchestrator agent or scoped locally to specific subagents.
MCP Configuration Scopes
| Scope | Configuration File | Virtual Agent Path | Description |
|---|---|---|---|
| Main Agent (Global) | ~/.ollama-agent/mcp.json |
/agent/mcp.json |
Global MCP tools available directly to the main agent orchestrator. |
| Subagent (Scoped) | ~/.ollama-agent/settings.yaml |
/agent/settings.yaml |
Dedicated MCP tools available only within an isolated subagent's execution graph. |
1. Main Agent MCP Configuration (/agent/mcp.json)
The global configuration file resides at /agent/mcp.json (persisted at ~/.ollama-agent/mcp.json). It uses JSON format with a top-level "mcpServers" object.
Schema & Supported Transports
A. Standard I/O Subprocess (stdio)
Runs an executable as a local subprocess communicating via stdio:
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/directory"],
"cwd": "/path/to/directory",
"env": {
"DEBUG": "true"
}
},
"github": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-github"],
"env": {
"GITHUB_PERSONAL_ACCESS_TOKEN": "${GITHUB_TOKEN}"
}
},
"git": {
"command": "uvx",
"args": ["mcp-server-git"]
}
}
}
command(string, required): Executable command (e.g.npx,uvx,python,node,docker, or binary path).args(array of strings, optional): Command-line arguments.cwd(string, optional): Working directory for the spawned process.env(object, optional): Environment variables. Values support${VAR}and%VAR%expansion from the host environment.transport(string, optional): Defaults to"stdio"whencommandis present.
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.
- 12d ago First seen · 170 lines · 43 tokens per session scan A 32bb79656730
mcp-configurator is a skill published in the GitHub repository arrase/ollama-agent (20 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 1,682 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
make-skill
A guided workflow for turning a conversation's solution into a reusable skill for coding agents.
copperhead
Change or verify a KiCad project through copperhead's gated pipeline. Use whenever a task touches .kicadsch or .kicadpcb files, a schematic, a PCB layout, a netlist, ERC/DRC, a BOM, or hardware design docs — instead of editing those files directly.
graphify
Turn any folder of files (code, docs, papers, images, video) into a queryable knowledge graph with community detection, an honest audit trail, and three outputs: interactive HTML, GraphRAG-ready JSON, and a plain-language GRAPHREPORT.md. Use when asked to analyze a codebase, understand architecture, map dependencies…
ollama
Use when running open-weight LLMs locally with Ollama — pulling and tagging models, calling the local API, picking a quantization or GGUF, writing Modelfiles, and sizing VRAM and RAM for the machine at hand. NOT remote or managed GPU serving and autoscaling (that is runpod), NOT downloading raw weights or datasets…
claude-api
Documentation content for this bundled skill was not part of the imported source tree.
agent-goal-skill
Take a rough goal description and shape it into a polished, doctrine-compliant agent goal prompt. Output is for the user to copy/paste into Codex, Claude Code (native /goal), Droid, Auggie, or any CLI agent that benefits from a structured goal contract. The skill does NOT execute the goal — it shapes the prompt and…