_ registry / mcp http-sse · checked 12h ago

living-atlas-kb

https://kb.l-a.site

Registry code: 4f3ab21bad8724e8

api record

Knowledge base service for Living Atlas / ALA repositories — semantic search over documentation, configuration, and source code, exposed as an MCP tool for AI assistants and as a REST API.

from a public catalogue that lists it, not from the operator

endpoint
https://kb.l-a.site/mcp
protocol
http-sse ·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 living-atlas-kb live?
Yes — it answered the hub's last check (checked 12h ago). It answered 100% of checks over the last 30 days.
Is living-atlas-kb free to use?
Yes — the hub reached it with no key and no payment.
What tools does living-atlas-kb have?
5 tools: query_ala_kb, answer_ala_kb, list_ala_kb_collections, get_ala_component_versions, get_ala_test_coverage.
Is living-atlas-kb 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
100%

90 days 100%· all time 100%

latency
240ms

last good check

priced tools
0

of 5 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
_ 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
3 open 2 never probed 3 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.

  • list_ala_kb_collections open 12h ago

    List available collections in the ALA Knowledge Base.

    mcp-tool

    {
      "type": "object",
      "title": "list_ala_kb_collectionsArguments",
      "properties": {}
    }
    arguments 5 lines
  • get_ala_component_versions open 12h ago

    Latest release/version of ALA components, from GitHub Releases. Pass repo as 'ORG/NAME' (e.g. 'AtlasOfLivingAustralia/collectory') for one component, or omit for all. Useful for keeping deployment dependency lists (e.g. la-toolkit-backend/assets/dependencies.yaml) up to date.

    mcp-tool

    {
      "type": "object",
      "title": "get_ala_component_versionsArguments",
      "properties": {
        "repo": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Repo",
          "default": null
        }
      }
    }
    arguments 18 lines
  • get_ala_test_coverage open 12h ago

    Test inventory of ALA / GBIF components: unit, integration and e2e case counts. Answers "how well tested is component X?" and "how does ALA compare with GBIF?". Counts declared test cases per framework (JUnit, Spock, pytest, Playwright, Geb, Cucumber), splits them by type, and reports which coverage tooling each build configures (jacoco, sonar, codecov, coveralls). This is NOT measured line coverage — that would need a full build per repo. Pass repo as 'ORG/NAME' for one component, org as e.g. 'gbif' to compare a whole organisation, or neither for everything.

    mcp-tool

    {
      "type": "object",
      "title": "get_ala_test_coverageArguments",
      "properties": {
        "org": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Org",
          "default": null
        },
        "repo": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Repo",
          "default": null
        }
      }
    }
    arguments 30 lines
  • query_ala_kb unknown never probed

    Query the ALA (Atlas of Living Australia) Knowledge Base. content_type: optionally restrict results to 'source' (production code), 'test' (test code — what a component actually checks), 'release' (GitHub release notes / changelogs), 'issue'/'pr', 'wiki' or 'faq'. Omit for all.

    mcp-tool

    {
      "type": "object",
      "title": "query_ala_kbArguments",
      "required": [
        "question"
      ],
      "properties": {
        "question": {
          "type": "string",
          "title": "Question"
        },
        "n_results": {
          "type": "integer",
          "title": "N Results",
          "default": 5
        },
        "collection": {
          "type": "string",
          "title": "Collection",
          "default": "la_toolkit_kb"
        },
        "content_type": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Content Type",
          "default": null
        }
      }
    }
    arguments 35 lines
  • answer_ala_kb unknown never probed

    Answer a question about the ALA / Living Atlas ecosystem. Unlike query_ala_kb (which returns raw chunks), this returns a synthesised answer composed by an LLM from the knowledge base, followed by a numbered list of the sources it cited. Best for non-Claude clients or when you want a ready-to-use answer; for your own synthesis, use query_ala_kb. content_type: optionally restrict retrieval to 'faq', 'wiki', 'source', 'test', 'release', 'issue' or 'pr'. Omit for all.

    mcp-tool

    {
      "type": "object",
      "title": "answer_ala_kbArguments",
      "required": [
        "question"
      ],
      "properties": {
        "question": {
          "type": "string",
          "title": "Question"
        },
        "n_results": {
          "type": "integer",
          "title": "N Results",
          "default": 8
        },
        "collection": {
          "type": "string",
          "title": "Collection",
          "default": "la_toolkit_kb"
        },
        "content_type": {
          "anyOf": [
            {
              "type": "string"
            },
            {
              "type": "null"
            }
          ],
          "title": "Content Type",
          "default": null
        }
      }
    }
    arguments 35 lines
_ try it 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 4f3ab21bad8724e8.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/4f3ab21bad8724e8/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/4f3ab21bad8724e8/badge.svg)](https://brick.blue/agent/4f3ab21bad8724e8?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 know
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.