From servicegraph
Finds and ranks directories/registries (e.g., smithery.ai, mcp.so) where you can submit an MCP server for backlinks and discovery. Drives the ServiceGraph API catalog.
How this skill is triggered — by the user, by Claude, or both
Slash command
/servicegraph:find-mcp-directoriesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Drive the **ServiceGraph API** (`https://api.servicegraph.co`) to find and
Drive the ServiceGraph API (https://api.servicegraph.co) to find and
rank directories and registries where a builder can list an MCP server
(Model Context Protocol) via the product_directory dataset. The catalog has
1,000+ directories; ~20 are dedicated MCP registries (e.g.
registry.modelcontextprotocol.io, smithery.ai, mcp.so, glama.ai,
pulsemcp.com), each enriched with Domain Rating (dr), backlinks, and
organic traffic.
This is a "where to publish / where to get backlinks" skill, not a "who to hire" skill. Each row is a registry you submit to, not a firm and not a server. The payoff is a backlink from a high-authority domain (SEO) plus discovery by agent builders browsing for servers.
Any HTTP client works (curl, fetch, requests). Examples below use curl.
find-ai-directories. (Several registries list
MCP servers and skills/tools — if the artifact is specifically an MCP
server, this skill is the right pick.)find-product-directories.If your harness has the ServiceGraph MCP server loaded (tool names contain
servicegraph), prefer those tools — credentials stay in the harness sandbox
via OAuth 2.1 + PKCE, no token in LLM context. Otherwise use the REST flow.
product_directory)Every endpoint requires the bearer (Authorization: Bearer vk_…).
| Endpoint | Cost | Use it for |
|---|---|---|
GET /v1/datasets/product_directory/fields[?include_values=1&q=] | free | Filter-field catalog + DSL grammar. Call first per session. |
GET /v1/datasets/product_directory/values/:field[?q=&limit=] | free | Enumerate values for one field. |
GET /v1/datasets/product_directory/check?filter=… | free | Validate a filter. |
POST /v1/datasets/product_directory/translate-intent | free | {intent} → DSL filter + sanity count. |
GET /v1/datasets/product_directory/search?filter=…&limit=&offset= | free | Brief cards (incl. dr) + per-row unlock hint + total. |
GET /v1/datasets/product_directory/:apex | free | Single row brief; gated fields only if unlocked. |
POST /v1/datasets/product_directory/unlocks | 10 credits / row | {apexes:[...]} ≤100. Atomic; 30-day TTL; was_cached:true free. |
GET /v1/me/credits | free | Balance. |
Cost model. Discovery / search / brief reads are free — including the dr
ranking signal. Unlocking a row costs 10 credits, lasts 30 days, and
reveals the gated fields: editor_note (how to submit + whether the
listing gives a backlink), organic_traffic, and total_visits.
Tokens are vk_* API keys. Keep the token out of the LLM context — never
read .env* into context; route authed calls through a shell wrapper.
Try the call through a wrapper that sources .env.local:
( set -a; [ -f .env.local ] && . ./.env.local; set +a;
curl -sS -H "Authorization: Bearer $SERVICEGRAPH_API_KEY" \
'https://api.servicegraph.co/v1/datasets/product_directory/fields' )
On 401, prompt the user (don't accept the key in chat):
"Open https://servicegraph.co/profile/api-keys, sign in, create a key, and add
SERVICEGRAPH_API_KEY=vk_…to.env.local(or export it). Tell me when done — please don't paste the key into chat."
Retry after the user signals ready.
GitHub-search-style. AND binds tighter than OR; comma list = OR within one
predicate; negation is -x / NOT x; any bareword is a keyword search
across the directory's name, title, description, listed metadata, and the
niche tag (so mcp matches dirs whose niche is "MCP servers"). Multiple
barewords AND; wrap multi-word phrases in double quotes.
mcp dr>=60
mcp OR "model context protocol"
mcp servers # → keyword:mcp AND keyword:servers
| Field | Free in brief? | Use it for |
|---|---|---|
dr | yes | Domain Rating 0–100 — the primary authority filter. Briefs come sorted by dr descending, so rank for free. |
referring_main_domains, backlinks, organic_keywords | yes (when populated) | Backlink-source strength signals. |
organic_traffic, total_visits | gated | Real reach. Filterable while hidden (organic_traffic>=1000); value shows after unlock. |
editor_note | gated | Submission instructions + backlink yes/no. |
industry, has | yes | Coarse refiners; for MCP the mcp keyword on niche is sharpest. |
Because dr is free and briefs are pre-sorted by it, rank a shortlist by
authority for zero credits — unlock only to reveal submission notes + traffic.
apexKeyed by apex domain (smithery.ai, not a full URL; subdomains like
registry.modelcontextprotocol.io are kept as-is when that's the catalog
key). Strip user-supplied URLs before :apex or unlock calls.
User: "Where should I list our new MCP server?"
GET /v1/datasets/product_directory/search?filter=mcp&limit=20
# → registry.modelcontextprotocol.io (dr 90), smithery.ai (75), glama.ai (72),
# mcp.so (72), cursor.directory (69), pulsemcp.com (68), … sorted by dr desc
Present the top N by dr (free).
User: "Only the registries with real domain authority for SEO."
GET /v1/datasets/product_directory/search?filter=mcp+dr>=60&limit=15
# → the ~7 strongest MCP registries by DR
organic_traffic is gated but filterable — gate to surface high-traffic
registries, then unlock to see the numbers:
GET /v1/datasets/product_directory/search?filter=mcp+organic_traffic>=2000&limit=15
Some registries list MCP servers alongside agent skills/tools. Cast wider when the strict-MCP pool is thin:
GET /v1/datasets/product_directory/search?filter=mcp OR "model context protocol" OR (agent skills)&limit=20
If the user's artifact is broader than MCP (general AI tool / agent skill),
defer to find-ai-directories.
# Present briefs ranked by dr (free). "Unlocking 6 = 60 credits, 30-day TTL —
# reveals each one's submission note (how + backlink yes/no) and traffic."
POST /v1/datasets/product_directory/unlocks
{ "apexes": ["smithery.ai", "mcp.so", "glama.ai", "pulsemcp.com", "cursor.directory", "registry.modelcontextprotocol.io"] }
Surface each editor_note verbatim — MCP registries vary a lot in submission
mechanics (some take a CLI/PR, some a web form) and in whether the listing
actually grants a backlink. The note tells the user before they spend effort.
GET /v1/datasets/product_directory/:apex per domain — free brief with dr
(404 = not in catalog, no charge). Flag misses, rank hits by dr.POST /unlocks (10×N credits, atomic) reveals notes + traffic.find-software-developer / find-ai-consultancy. "How does MCP work" is a
DIY question, not this dataset.dr is free and briefs are pre-sorted by it — rank for zero credits.organic_traffic>=1000).find-ai-directories.model context protocol = three AND'd
keywords; "model context protocol" is one phrase.JSON envelope: {"error": {"code": "...", "message": "..."}}.
| Status | Code | What to do |
|---|---|---|
| 400 | filter_parse_error | position included; fix and re-validate with /check. |
| 400 | field_not_in_dataset | Drop the field. |
| 400 | invalid_apex | Re-normalize to apex. |
| 401 | unauthorized | Re-prompt for a fresh vk_…. |
| 402 | insufficient_credits | needed/balance in payload; nothing charged. |
| 404 | not_found / not_in_dataset | Apex not in dataset. Skip; not charged. |
| 429 | rate_limited | Honor Retry-After. |
User: "We just shipped an MCP server. Find the highest-authority registries to list it on, and tell me how to submit to the top five."
# 1. Discover (once per session)
GET /v1/datasets/product_directory/fields?include_values=1
# 2. Validate + scope (free)
GET /v1/datasets/product_directory/check?filter=mcp+dr>=50
# 3. Search briefs (free) — pre-sorted by dr desc
GET /v1/datasets/product_directory/search?filter=mcp+dr>=50&limit=20
# 4. User picks 5. "Unlocking 5 = 50 credits, 30-day TTL — reveals submission
# notes (how + backlink yes/no) and traffic."
# 5. Atomic unlock (charges 50 credits)
POST /v1/datasets/product_directory/unlocks
{ "apexes": ["smithery.ai", "mcp.so", "glama.ai", "pulsemcp.com", "cursor.directory"] }
# 6. Surface each editor_note verbatim + traffic so the user can prioritize.
npx claudepluginhub nostrband/servicegraph --plugin servicegraphFinds and ranks directories for submitting software products (SaaS, apps, tools) to get backlinks and launch traffic. Uses ServiceGraph API with SEO metrics.
MCPize Idea Finder — find a profitable MCP server idea, validate it, and get a ready-to-build brief. Part of the MCPize suite (mcpize.com). Guides users through discovery interview (up to 10 questions about skills, domain, goals), generates tailored MCP server ideas, researches competitors across MCP marketplaces, analyzes monetization potential with pricing models, and outputs a structured brief/PRD. Use this skill whenever someone wants to brainstorm, find, discover, or validate an MCP server idea, asks what MCP server to build, wants to explore MCP business opportunities, or says they want to build an MCP but don't know what kind. Also trigger on: mcpize idea, mcp idea, what mcp to build, mcp server business, find mcp idea.
Guides developers on submitting products to directories for dofollow backlinks and discovery. Covers strategy, ordering, and positioning to maximize link equity.