_ registry / mcp + a2a streamable-http · checked 2h ago

skillselion

https://skillselion.com

Registry code: c3c6dcc6fd4500e7

api record

This is the Skillselion PRODUCT catalog MCP (actions: search, load a listing into the current task, synthesize rules across skills, leaderboard, catalog stats). Skills rank by tracked installs. MCP servers and marketplaces rank by GitHub stars when `type` is mcp or marketplace; with no `type`, results are ordered by installs, so MCP server and marketplace order is arbitrary. Rankings are a community signal, not a safety audit. It is not the website-docs MCP. Docs live at https://skillselion.com/.well-known/mcp/docs. Tools: search_skillselion, load_skill, synthesize_skills, top_skillselion,…

endpoint
https://skillselion.com/mcp
door code
49ff503dcca60db9
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is skillselion live?
Yes — it answered the hub's last check (checked 2h ago). It answered 100% of checks over the last 30 days.
Is skillselion free to use?
Yes — the hub reached it with no key and no payment.
What tools does skillselion have?
5 tools: synthesize_skills, load_skill, search_skillselion, top_skillselion, get_catalog_stats.
Is skillselion safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
99.7%

90 days 99.5%· all time 99.8%

latency
288ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 1236 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • degraded → live
  • degraded → live
_ what it is for
used for
  • search a catalog of agent skills and mcp servers
  • load a skill into the current task
  • list most-installed skills
takes → gives
text → data, text
tools
4 reads
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 5 tools
4 open 1 never probed 4 of 5 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • load_skill reads open 21h ago

    Load one Skillselion catalog listing (and its SKILL.md when stored) into the current task without installing it.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "Skillselion listing id or owner/repo#slug."
        },
        "context": {
          "type": "string",
          "description": "Optional. Accepted for compatibility; not used for ranking on this tool."
        }
      }
    }
    arguments 16 lines
  • search_skillselion reads open 18h ago

    Search the Skillselion product catalog of agent skills, MCP servers and marketplaces. Results are ordered by relevance first, then by the ranking signal. Skills rank by tracked installs. MCP servers and marketplaces rank by GitHub stars when `type` is mcp or marketplace; with no `type`, results are ordered by installs, so MCP server and marketplace order is arbitrary. Rankings are a community signal, not a safety audit.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "type": {
          "enum": [
            "skill",
            "mcp",
            "marketplace",
            "plugin"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "maximum": 25,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "description": "The task or domain in plain words: 2-4 words, ONE topic (e.g. \"typescript code review\", \"github issues\", \"playwright testing\"). The catalog matches EVERY word, so more words return fewer results. If nothing matches, retry with FEWER words."
        },
        "context": {
          "type": "string",
          "description": "Optional. Accepted for compatibility; not used for ranking on this tool."
        }
      }
    }
    arguments 30 lines
  • top_skillselion reads open 21h ago

    Return the current top Skillselion catalog listings (the leaderboard), optionally for one type. Skills rank by tracked installs. MCP servers and marketplaces rank by GitHub stars when `type` is mcp or marketplace; with no `type`, results are ordered by installs, so MCP server and marketplace order is arbitrary. Rankings are a community signal, not a safety audit.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "type": {
          "enum": [
            "skill",
            "mcp",
            "marketplace"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "maximum": 25,
          "minimum": 1
        }
      }
    }
    arguments 18 lines
  • get_catalog_stats reads open 21h ago

    Product action: return live Skillselion catalog totals (listings, skills, MCP servers, marketplaces, installs). Not website docs.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "detail": {
          "enum": [
            "summary",
            "full"
          ],
          "type": "string",
          "description": "summary is the default totals object; full is the same totals (no extra private fields)."
        }
      }
    }
    arguments 13 lines
  • synthesize_skills unknown 18h ago

    Merge the key rules of the top matching Skillselion skills into one cross-source playbook. Reads the stored SKILL.md of each source skill and returns a deduped rule digest, every rule tagged with its source skill and each source named with its listing URL. Use it for broad "how should I approach X" tasks that span several skills; use load_skill for one specific skill.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "query": {
          "type": "string",
          "description": "The topic or task to synthesize across skills (e.g. \"playwright e2e testing\")."
        },
        "context": {
          "type": "string",
          "description": "Optional. Your stack and constraints (e.g. \"Next.js 15 App Router, TypeScript\"). A ranking hint only, never matched as keywords and never required."
        }
      }
    }
    arguments 16 lines
_ try it over mcp through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id c3c6dcc6fd4500e7.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/c3c6dcc6fd4500e7/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/c3c6dcc6fd4500e7/badge.svg)](https://brick.blue/agent/c3c6dcc6fd4500e7?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we knowoff the mcp door
card completeness
90%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.