Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Search a curated directory of ISO 27001, SOC 2 and compliance services, with listing checks.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"complydir": {
"command": "npx",
"args": [
"-y",
"@reneturcios/complydir",
"mcp"
]
}
}
}Run this in your terminal
claude mcp add complydir -- npx -y @reneturcios/complydir mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"complydir": {
"command": "npx",
"args": [
"-y",
"@reneturcios/complydir",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"complydir": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/complydir",
"mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified with the GitHub account CloudCorpRecords, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.1.0) reached the registry 2 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js, Docker on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A directory of compliance help, searchable from your agent. complydir wraps a curated catalog of services that work on ISO 27001, SOC 2, DORA and neighbouring frameworks — consultancies, auditors and software — published as a single catalog snapshot. There is no account and no API key: the tools fetch the snapshot, answer questions about it locally, and can queue a new free listing for review.
Because search happens over the snapshot rather than a remote search call, the filter rules are exact and predictable. Tag filters never do substring matching: asking for the region "Germany" returns services tagged Germany, and asking for two frameworks returns only services tagged with both.
search_services — multi-filter catalog search. All parameters are optional, but at least one is required: query (free text used to rank the filtered set), framework (a single framework), frameworks (several frameworks, ANDed together), region, industry, service_type, and limit (1–25, default 10). Tag matches are case-insensitive and exact, and a service_type of "Consulting" also matches services tagged "Consultants". For example, frameworks ["ISO 27001", "DORA"] with region "Germany" and service_type "Consulting" returns German services covering both frameworks that consult.check_if_listed — whether a company is in the catalog. Takes a required company_name (for example "Scrut Automation") and answers with the matched record when it is listed.get_service_details — the full catalog record for one service, by its required service_name (for example "Compleye").list_categories — the distinct values in one dimension of the catalog, with counts. dimension is one of frameworks, regions, industries, service_types or problems; omit it to get every dimension at once.submit_listing — queue a free listing (the one write tool). Required: name, url (http or https), email (a contact address, not shown publicly) and brief_summary (10–300 characters). Optional: description, linkedin, service_type, region_covered and compliance_framework_expertise. Confirm the name, website, contact email and one-line summary with the user before calling — a queued listing goes into the same review queue as the free web form and is not live instantly.The read tools fetch the public snapshot from https://ismsdirectory.com/api/tools.json and run over it in memory; submit_listing posts to https://ismsdirectory.com/api/submit. Both go through one injectable fetch function, which is how the test suite exercises everything against a small hand-built snapshot with no live calls.
Two shapes are labelled reconstructions, because the published material pins the fields rather than the record layout: the per-service record fields beyond a service's name and its framework, region, industry and service-type tags, and the tools' output objects. Outputs are built around the pinned fields — the service name, its tags and the filters that matched.
Failures read plainly: a non-2xx upstream reply is complydir error: HTTP , an unreachable upstream is complydir unreachable, and a snapshot that does not parse as a list of records is complydir snapshot invalid.
Each tool is a subcommand taking one JSON argument string:
npx @reneturcios/complydir search_services '{"frameworks":["ISO 27001","DORA"],"region":"Germany","service_type":"Consulting"}'
npx @reneturcios/complydir check_if_listed '{"company_name":"Scrut Automation"}' npx @reneturcios/complydir get_service_details '{"service_name":"Compleye"}' npx @reneturcios/complydir list_categories '{"dimension":"frameworks"}' npx @reneturcios/complydir submit_listing '{"name":"Acme Compliance","url":"https://acme.example","email":"hello@acme.example","brief_summary":"ISO 27001 consulting for SaaS"}' npx @reneturcios/complydir --version
Exit codes: 0 on success, 1 on a runtime error, 2 on a usage error.
npx -y @reneturcios/complydir mcp
MCP client config:
{
"mcpServers": { "complydir": { "command": "npx", "args": ["-y", "@reneturcios/complydir", "mcp"] } } }
docker run -i ghcr.io/cloudcorprecords/complydir
docker run --rm ghcr.io/cloudcorprecords/complydir list_categories '{"dimension":"regions"}'
npm install
npm run build # tsc -> dist/ npm test # tsx --test test/*.test.ts (fake fetch only, no network) npm run dev # run the CLI from source
MIT — Copyright (c) 2026 Rene Turcios