# LocalMark Agent Directory

> Search public A2A agents and inspect read-only Agent Card and endpoint checks.

- name: ai.localmark/agent-directory
- version: 1.0.1
- connection class: R0 (autonomous)
- trust: 82/100 flags: no-repository
- quality: 73/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/ai.localmark%2Fagent-directory
- tools: https://api.protogrid.dev/v1/servers/ai.localmark%2Fagent-directory/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent-directory": {
      "type": "http",
      "url": "https://localmark.ai/mcp"
    }
  }
}
```


## Trust

- hygiene: 80
- liveness: 99
- freshness: 100
- provenance: 55
- drivers: +dns-namespace +website +reachable +uptime-98% +updated-9d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 73/100 (needs work)

### protocol: 88 (weight 25)

- pass `protocol.modern`: supports 2026-07-28 (server/discover)
- pass `protocol.stateless`: answers without a session
- pass `protocol.transport`: streamable HTTP
- warn `protocol.list_ttl`: tools/list declares ttlMs 0, so clients re-fetch it on every use

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 6 of 6 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: get_connection_plan (openWorldHint); recommend_agents (openWorldHint); get_agent (openWorldHint); …
- pass `tools.token_cost`: about 960 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 25 (weight 15)

- warn `stability.changes`: 7 tool changes in 30 days
- fail `stability.rug_pull`: 2 tools kept their name but changed most of their description in 30 days; review before trusting them

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 6, about 960 tokens to load them all
- tool set hash: 99e0a48d53aff9f80955295ac366df38
- tools last changed: 2026-10-20T10:08:01.648Z
- badge: [![protogrid quality](https://protogrid.dev/badge/ai.localmark/agent-directory.svg)](https://protogrid.dev/servers/ai.localmark/agent-directory)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `verify_agent` changed (description) **meaning changed**
  - before: Read LocalMark's stored checks, publisher claim and recent card changes for an exact public Agent Card URL. No live request is made to the publisher.
  - after: Read stored checks for a card URL, endpoint URL or publisher domain. Unseen targets return listing_status 'not_seen', including available lookalike-domain hints. Publisher domains may return multiple matches. No live request is made to the publisher.
- 2026-10-20 `get_connection_plan` added
  - Read connection metadata for a public agent without connecting to it. Accepts a LocalMark agent ID, Agent Card URL, endpoint URL or domain. Returns advertised interfaces, authentication scheme metadata, input/output modes, skill names and stored evidence. A publisher domain may be ambiguous. The plan never includes credentials and never authorizes a task or payment. Obtain explicit task authorization before using any endpoint.
- 2026-10-20 `recommend_agents` added
  - Recommend agents for a capability or job with matching reasons and caveats. Uses exactly the website/API ranking and stored observations, never a live task. Filters are requirements, so an empty shortlist is valid. auth is 'none' or 'declared'; signature is 'verified'; protocol is JSONRPC, HTTP+JSON or GRPC. Observation age is 1..168 hours. max_amount is a non-negative amount in human-readable asset units (0.05 means 0.05 USDC for a USDC asset) and requires both network and asset with known decimals. No price conversion across assets is performed. Returns full structured results, total_matches, pagination, ranking_version and evidence scope.
- 2026-10-11 `verify_agent` added
  - Read LocalMark's stored checks, publisher claim and recent card changes for an exact public Agent Card URL. No live request is made to the publisher.
- 2026-10-08 `get_agent` changed (annotations)
- 2026-10-08 `list_agents` changed (description, annotations) **meaning changed**
  - before: Browse published agents in alphabetical order with stable pagination.
  - after: Browse public agents with pagination.
- 2026-10-08 `search_agents` changed (annotations)

Full history: https://api.protogrid.dev/v1/servers/ai.localmark%2Fagent-directory/changes

## Remotes

- https://localmark.ai/mcp (streamable-http, auth none, reachable true, uptime30d 0.9811321)

## Packages

_none_

## Tools (6)

- `get_agent`: Get one published agent's source, declared skills, and latest card check by LocalMark ID.
- `get_connection_plan`: Read connection metadata for a public agent without connecting to it.

    Accepts a LocalMark agent ID, Agent Card URL, endpoint URL or domain.
    Returns advertised interfaces, authentication scheme metadata, input/output
    modes, skill names and stored evidence. A publisher domain may be
    ambiguous. The plan never includes credentials and never authorizes a task
    or payment. Obtain explicit task authorization before using any endpoint.
    
- `list_agents`: Browse public agents with pagination.
- `recommend_agents`: Recommend agents for a capability or job with matching reasons and caveats.

    Uses exactly the website/API ranking and stored observations, never a live
    task. Filters are requirements, so an empty shortlist is valid. auth is
    'none' or 'declared'; signature is 'verified'; protocol is JSONRPC,
    HTTP+JSON or GRPC. Observation age is 1..168 hours. max_amount is a
    non-negative amount in human-readable asset units (0.05 means 0.05 USDC
    for a USDC asset) and requires both network and asset with known decimals.
    No price conversion across assets is performed. Returns full structured
    results, total_matches, pagination, ranking_version and evidence scope.
    
- `search_agents`: Search public agent names, descriptions, and declared skills. Returns card and profile URLs, not task results.
- `verify_agent`: Read stored checks for a card URL, endpoint URL or publisher domain.

    Unseen targets return listing_status 'not_seen', including available
    lookalike-domain hints. Publisher domains may return multiple matches.
    No live request is made to the publisher.