okf-mcp

okf-mcp is a skill for Claude Code, Codex from xSAVIKx/okf-skills. It costs 67 tokens per session (645 once invoked), scanned A, original, Apache-2.0.

A bridge between OKF command-line tools and MCP, a standard that lets AI coding assistants call external tools. It discovers installed OKF skill programs and exposes their commands as callable MCP tools.

In plain words
What is it for?
Use it to discover OKF tools, read their machine-readable command definitions, and run their produce or ingest commands through an MCP-capable assistant.
Why use it?
It removes the need to connect each OKF command-line program to an MCP-compatible assistant separately.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; mentions Gemini CLI.

Good fit Use it to discover OKF tools, read their machine-readable command definitions, and run their produce or ingest commands through an MCP-capable assistant.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xsavikx/okf-skills/okf-mcp
Install

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.

Any agent
npx skills add xSAVIKx/okf-skills --skill okf-mcp
Clone the repo
git clone --depth 1 https://github.com/xSAVIKx/okf-skills

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for okf-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-mcp/github.svg)](https://agentmods.dev/skills/xsavikx/okf-skills/okf-mcp)
Your own site
<a href="https://agentmods.dev/skills/xsavikx/okf-skills/okf-mcp"><img src="https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-mcp/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.

agentmods 80×15 button for okf-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/xsavikx/okf-skills/okf-mcp"><img src="https://agentmods.dev/badge/skills/xsavikx/okf-skills/okf-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 645 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00067 $0.00645
Opus 5 $0.00034 $0.00322
Sonnet 5 $0.00013 $0.00129
Haiku 4.5 $0.00007 $0.00064

Measured 11d ago against content hash 39a63a1e1036, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

okf-mcp 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 11d 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.

okf-mcp/SKILL.md · 53 lines

What it actually says

OKF MCP Server

okf-mcp is a generic Model Context Protocol server. On startup it discovers installed okf-* skill binaries, runs <skill> schema on each, and exposes every skill command (except schema itself) as an MCP tool named <skill>__<command> (e.g. okf-sqlite__produce). Any MCP-capable harness can then drive all of OKF Skills without per-skill glue.

How it works

  1. Discovery — scans --skills-dir, else $OKF_SKILLS_DIR, else every $PATH entry, for okf-* executables.
  2. Reflection — reads each skill's machine-readable schema output and turns its flags into a JSON-Schema tool input.
  3. Invocation — a tool call is translated back into the skill's CLI (<command> --flag value ...) and run with a per-call timeout. Flags that advertise an env binding (e.g. database passwords) are passed via the child environment, never argv. The skill's stdout is returned as the tool result.

Install

Install the published server binary (Go 1.24+) — no clone needed:

go install github.com/xSAVIKx/okf-skills/[email protected]

This drops an okf-mcp binary into $(go env GOPATH)/bin. Alternatively, build from a clone: cd okf-mcp && go build -o okf-mcp .

Running

okf-mcp                      # discover skills on PATH, serve over stdio
okf-mcp --skills-dir ./bin   # discover skills in a specific directory
okf-mcp --timeout 2m         # per-invocation timeout (default 5m)

Diagnostics are written to stderr; stdout is the MCP protocol channel.

Configuring a harness

Point any MCP client at the okf-mcp command over stdio. Example (generic MCP client config):

{
  "mcpServers": {
    "okf": { "command": "okf-mcp", "args": ["--skills-dir", "/path/to/okf/bin"] }
  }
}
Files

What ships with it

11 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.

Changes

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.

  1. 11d ago First seen · 53 lines · 67 tokens per session scan A 39a63a1e1036

Subscribe to this mod's changes

okf-mcp is a skill published in the GitHub repository xSAVIKx/okf-skills (33 stars, last pushed 11d ago), licensed Apache-2.0. It adds 67 tokens to every session and 645 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.

Related

Other skills, from other repositories

okf-authoring

Author Open Knowledge Format (OKF) bundles — knowledge represented as a directory of markdown files with YAML frontmatter. Use when asked to create, write, generate, enrich, or validate an OKF bundle or OKF concept docs; to turn a data source (Glue database, API, database, catalog), documentation, or a research topic…

aws-samples/sample-okf-llm-wiki · 102 tokens

refresh-okf-mcp-token

Fetch or refresh an OAuth2 access token for the OKF Data wiki consumption MCP server. Use when the OKF MCP server returns 401/403/unauthorized/expired-token errors, when the user asks to refresh, renew, or get a new OKF MCP token, or when setting up authentication to call the okf-mcp / okfconsumption MCP runtime.

aws-samples/sample-okf-llm-wiki · 83 tokens

report-authoring

The report-authoring methodology: required structure, language, evidence discipline, and figure selection. Read BEFORE your first createreport of a conversation - the tool validates shape; this is everything it cannot check.

aws-samples/sample-okf-llm-wiki · 44 tokens

setup

Set up the OKF MCP plugin — outputs a guide for the user to create their /.okf/credentials file with their OAuth2 client id/secret. Use when first enabling the plugin, when headersHelper fails with "Missing credentials", or when the user says "setup okf".

aws-samples/sample-okf-llm-wiki · 60 tokens

create-custom-grader

Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.

NVIDIA/SkillEvaluator · 35 tokens

agent-ready-cloudflare

Audit and improve website readiness for AI agents using the Cloudflare "Is It Agent Ready?" scanner (isitagentready.com). Covers scanning via API, interpreting results, generating implementation prompts, and fixing every check. Use when the user mentions "agent ready", "isitagentready", "AI agent scan", "agent…

fabricioctelles/skills · 158 tokens