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 mcp2cli/source-code --skill filesgit clone --depth 1 https://github.com/mcp2cli/source-codeWrote 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/mcp2cli/source-code/files)<a href="https://agentmods.dev/skills/mcp2cli/source-code/files"><img src="https://agentmods.dev/badge/skills/mcp2cli/source-code/files/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/mcp2cli/source-code/files"><img src="https://agentmods.dev/badge/skills/mcp2cli/source-code/files.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00060 | $0.01675 |
| Opus 5.5 | $0.00024 | $0.00670 |
| Sonnet 5.5 | $0.00012 | $0.00335 |
| Haiku 4.5 | $0.00006 | $0.00168 |
Grade A, and why
mcp2cli 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 1mo 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: mcp2cli
This skill enables AI agents and coding assistants to work effectively with
the mcp2cli CLI tool — both as users invoking it from the terminal and as
contributors editing its source code.
When to Activate This Skill
Use this skill when the user:
- Asks how to run a command against an MCP server from the terminal
- Wants to create a named config, symlink alias, or set an active config
- Needs to parse or transform
mcp2cli --jsonoutput withjq - Is writing a shell script or CI pipeline that calls MCP tools
- Is implementing an AI agent loop that invokes MCP tools via
mcp2cli - Is editing source files under
src/ - Asks about the MCP protocol, transports, or capability discovery
- Wants to install or regenerate man pages for
mcp2clior an alias
Key Concepts
Two modes
| Mode | When to use | How |
|---|---|---|
| Ad-hoc | Exploration, one-off scripts, CI | mcp2cli --url URL COMMAND or mcp2cli --stdio CMD COMMAND |
| Named config + alias | Daily use, multiple servers | mcp2cli config init, mcp2cli link create, then use the alias directly |
Dispatch routing
argv[0] == "mcp2cli"→ host mode (config/link/use/man/daemon commands)argv[0] == "<alias>"→ bridge mode (MCP runtime commands for that named config)mcp2cli <config-name> <command>→ bridge mode with explicit config name
JSON output
Every command supports --json. The response envelope is:
{
"app_id": "<alias>",
"command": "<command>",
"summary": "<one-line>",
"lines": ["..."],
"data": { ... }
}
Pipe to jq for scripting: email --json ls | jq '.data.items[].id'
Common Tasks
Discover what a server offers
# Ad-hoc
mcp2cli --url http://localhost:3001/mcp ls
mcp2cli --url http://localhost:3001/mcp ls --tools
mcp2cli --url http://localhost:3001/mcp ls --resources
# Named alias
email ls
email ls --prompts
email ls --filter "draft"
Call a tool
# Ad-hoc
mcp2cli --url http://localhost:3001/mcp echo --message hello
# Named alias
email send --to [email protected] --subject "Hi" --body "Hello"
email search --query "from:boss"
email reply --thread-id 123 --body "Thanks"
What ships with it
4 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.
- 1mo ago First seen · 228 lines · 60 tokens per session scan A be80f9ebce9b
mcp2cli is a skill published in the GitHub repository mcp2cli/source-code (12 stars, last pushed 26d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,675 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
connect
Connect any AI agent to MCP servers through mcptoon — one config synced everywhere, one stdio gateway, 99.2% fewer tokens on tool discovery.
authoring
Add or edit an MCP server entry in mcptoon's config correctly — stdio/streamable-http/sse shapes, command rules, placeholders, and validation.
triage
Diagnose and fix broken MCP servers in mcptoon — doctor, health, per-server probes, and the common failure playbook.
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
mcptoon
Compress MCP tool discovery with the mcptoon CLI. Trigger when a session has a large MCP tool catalog (many servers/tools), when the user mentions token cost, tool discovery, mcptoon, or asks to list/call MCP tools efficiently. Also route here when the user says the MCP tool list is too large, the agent context window…
zenith
Author and modify editable .zen designs with the Zenith CLI. Use for posters, slides, diagrams, charts, brand kits, size variants, and CSV mail-merge. Export PNG, self-contained SVG with outlined text, or PDF with explicit raster fallback reports. Use other tools for photo generation, raster editing, and unrelated…