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 agntcy/dir-mcp --skill configure-dir-mcpgit clone --depth 1 https://github.com/agntcy/dir-mcpWrote 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/agntcy/dir-mcp/configure-dir-mcp)<a href="https://agentmods.dev/skills/agntcy/dir-mcp/configure-dir-mcp"><img src="https://agentmods.dev/badge/skills/agntcy/dir-mcp/configure-dir-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.
<a href="https://agentmods.dev/skills/agntcy/dir-mcp/configure-dir-mcp"><img src="https://agentmods.dev/badge/skills/agntcy/dir-mcp/configure-dir-mcp.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 | $0.00072 | $0.02269 |
| Opus 5.5 | $0.00029 | $0.00908 |
| Sonnet 5.5 | $0.00014 | $0.00454 |
| Haiku 4.5 | $0.00007 | $0.00227 |
Grade B, and why
configure-dir-mcp scanned grade B with 1 finding 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.
Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
cat .mcp.json How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure dir-mcp
dir-mcp keeps no config file of its own. Two independent things can be configured, and it's important not to conflate them:
- The MCP server's own directory connection — used by every
agntcy_dir_*/agntcy_oasf_*tool call. Set viaDIRECTORY_CLIENT_*environment variables in.mcp.json'senvblock. This is what to edit when the user asks to "configure dir-mcp". - The bundled
dirctlCLI's own target server — used only whendirctlitself is invoked directly (e.g. by thedirctl-authorsearch-agentsskills). It has a separate config file with named contexts at~/.config/dirctl/config.yaml.DIRECTORY_CLIENT_*env vars, if set, overridedirctl's selected context too — so setting them once in.mcp.json'senvblock keeps both in sync automatically.dirctlcontexts are only useful as an extra convenience for switching directories across plain terminal invocations ofdirctloutside of Claude Code.
This skill covers (1), the MCP server's own connection. See the dirctl-auth skill if you specifically need to manage dirctl contexts.
1. Find the MCP config file
cat .mcp.json
Locate the agntcy-dir entry's env block (create one if it doesn't exist yet).
2. Understand the options
| Key | Default | Purpose |
|---|---|---|
OASF_API_VALIDATION_SCHEMA_URL |
https://schema.oasf.outshift.com |
OASF schema server used for validation, get_schema, and taxonomy lookups |
DIRECTORY_CLIENT_SERVER_ADDRESS |
0.0.0.0:8888 |
Address of the AGNTCY Directory server (host:port) |
DIRECTORY_CLIENT_AUTH_MODE |
none |
Auth mode for the Directory client — see modes below |
DIRECTORY_CLIENT_AUTH_TOKEN |
(empty) | Pre-issued bearer token; skips interactive login |
DIRECTORY_CLIENT_OIDC_ISSUER |
(empty) | OIDC issuer URL (required for oidc mode) |
DIRECTORY_CLIENT_OIDC_CLIENT_ID |
(empty) | OIDC client ID (required for oidc mode) |
DIRECTORY_CLIENT_SPIFFE_SOCKET_PATH |
(empty) | SPIFFE Workload API socket path (for x509/jwt modes) |
DIRECTORY_CLIENT_SPIFFE_TOKEN |
(empty) | Path to SPIFFE token file (for token mode) |
DIRECTORY_CLIENT_JWT_AUDIENCE |
(empty) | JWT audience claim (for jwt mode) |
DIRECTORY_CLIENT_TLS_CERT_FILE |
(empty) | Client TLS certificate file (for tls mode) |
DIRECTORY_CLIENT_TLS_KEY_FILE |
(empty) | Client TLS private key file (for tls mode) |
DIRECTORY_CLIENT_TLS_CA_FILE |
(empty) | CA certificate for server verification (for tls mode) |
DIRECTORY_CLIENT_TLS_SKIP_VERIFY |
(empty) | Set to true to skip TLS certificate verification |
DIRECTORY_MCP_PATH |
(bundled binary) | Absolute path to the dir-mcp server binary; overrides the binary bundled in the npm package |
DIRECTORY_DIRCTL_PATH |
(bundled binary) | Absolute path to the dirctl binary; overrides the binary bundled in the npm package |
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 Changed · +16 lines · +2 tokens per session scan A → B 348905325923
- 1mo ago Changed · +39 tokens per session 48a6aba53bf4
- 2mo ago First seen · 174 lines · 31 tokens per session scan A 0037e453eeb8
configure-dir-mcp is a skill published in the GitHub repository agntcy/dir-mcp (4 stars, last pushed 3d ago), licensed Apache-2.0. It adds 72 tokens to every session and 2,269 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…