_ registry / mcp http-sse · checked 1h ago

ruagentic-directory

https://ruagentic.com

Registry code: bc593942cd0ef987

api record

RUAGENTIC (ruagentic.com) is a public directory of MCP servers, MCP clients, AI agents, skills, plugins, rules files and evals, updated daily from public sources and owner submissions.

Use search_directory to find listings, get_listing for one listing's facts and how to connect, connect_instructions for the exact config for a client, top_listings for rankings, new_listings for recent additions, compare_listings for side-by-side facts, and directory_overview for the kinds and categories that exist.

endpoint
https://ruagentic.com/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 ruagentic-directory live?
Yes — it answered the hub's last check (checked 1h ago). It answered 98% of checks over the last 30 days.
Is ruagentic-directory free to use?
Yes — the hub reached it with no key and no payment.
What tools does ruagentic-directory have?
7 tools: compare_listings, connect_instructions, get_listing, top_listings, directory_overview, new_listings, search_directory.
Is ruagentic-directory 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
98.1%

90 days 98.8%· all time 98.8%

latency
258ms

last good check

priced tools
0

of 7 tools

_ answered our checks, 90 days 344 checks · signed record
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
  • live → degraded· timeout after 20000ms
  • degraded → live
_ what it is for
used for
  • search a directory of mcp servers and agents
  • get connection config for an mcp server
  • compare mcp listings
  • list new and top listings
takes → gives
text → data
tools
7 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 7 tools
3 open 4 never probed 3 of 7 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.

  • directory_overview reads open 1h ago

    What the directory contains: the seven kinds and twenty categories with current counts and browse URLs. Call it to choose valid filters.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {},
      "additionalProperties": false
    }
    arguments 6 lines
  • new_listings reads open 1h ago

    Listings added to RUAGENTIC in the last N days (1–90), newest first, optionally one kind.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "days": {
          "type": "integer",
          "default": 7,
          "maximum": 90,
          "minimum": 1
        },
        "kind": {
          "enum": [
            "server",
            "client",
            "product",
            "skill",
            "plugin",
            "rules",
            "eval"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "default": 20,
          "maximum": 50,
          "minimum": 1
        }
      },
      "additionalProperties": false
    }
    arguments 31 lines
  • search_directory reads open 1h ago

    Search RUAGENTIC listings by words, with optional filters. Use when someone asks for an MCP server, client, AI agent, skill, plugin, rules file or eval for a task, a product, a category or a platform. Returns ranked listings with public GitHub stars, launch date and listing URL. server = MCP server, client = MCP client, product = AI agent, skill = Agent Skills package (SKILL.md), plugin = plugin or extension for an agent host, rules = rules or instruction file (CLAUDE.md, AGENTS.md, .cursorrules), eval = benchmark or evaluation set.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "kind": {
          "enum": [
            "server",
            "client",
            "product",
            "skill",
            "plugin",
            "rules",
            "eval"
          ],
          "type": "string"
        },
        "sort": {
          "enum": [
            "relevance",
            "stars",
            "newest",
            "name"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1
        },
        "query": {
          "type": "string",
          "default": "",
          "maxLength": 200
        },
        "offset": {
          "type": "integer",
          "default": 0,
          "maximum": 5000,
          "minimum": 0
        },
        "category": {
          "type": "string",
          "maxLength": 80,
          "description": "A category name from directory_overview, e.g. \"Developer tools\"."
        },
        "launched": {
          "enum": [
            "any",
            "30d",
            "90d",
            "year",
            "older"
          ],
          "type": "string"
        },
        "minStars": {
          "type": "integer",
          "maximum": 1000000,
          "minimum": 0
        },
        "platform": {
          "type": "string",
          "maxLength": 40,
          "description": "An agent or platform the listing says it works with, e.g. \"Cursor\"."
        },
        "verifiedOnly": {
          "type": "boolean",
          "description": "Only listings whose Agentic Protocol files passed the checker."
        }
      },
      "additionalProperties": false
    }
    arguments 74 lines
  • compare_listings reads unknown 9h ago

    Side-by-side published facts for two to five listings: stars, pricing, transport, authentication, platforms, capabilities, license, repository and endpoint.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "slugs"
      ],
      "properties": {
        "slugs": {
          "type": "array",
          "items": {
            "type": "string",
            "pattern": "^[a-z0-9-]{1,150}$"
          },
          "maxItems": 5,
          "minItems": 2
        }
      },
      "additionalProperties": false
    }
    arguments 19 lines
  • connect_instructions reads unknown 9h ago

    The exact configuration to add a listed MCP server to a client: Claude Code (command), Cursor, Windsurf or Claude Desktop (mcpServers JSON), or Codex (config.toml table). Built from the listing’s published endpoint or package; required credentials are left as <value> placeholders.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "slug",
        "client"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9-]{1,150}$"
        },
        "client": {
          "enum": [
            "claude-code",
            "cursor",
            "claude-desktop",
            "codex",
            "windsurf"
          ],
          "type": "string"
        }
      },
      "additionalProperties": false
    }
    arguments 25 lines
  • get_listing reads unknown 9h ago

    Read one RUAGENTIC listing by slug: published facts, GitHub stars, how to connect (endpoint, package, required credentials, snippets, CLI command) and the questions people ask about it. Does not install or run anything.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "slug"
      ],
      "properties": {
        "slug": {
          "type": "string",
          "pattern": "^[a-z0-9-]{1,150}$"
        }
      },
      "additionalProperties": false
    }
    arguments 14 lines
  • top_listings reads unknown 6h ago

    The most-starred listings of a kind (public GitHub stars), or the fastest-growing since launch (stars per day since the repository was created). Optional category. Stars measure attention, not quality.

    mcp-tool

    {
      "type": "object",
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "required": [
        "kind"
      ],
      "properties": {
        "by": {
          "enum": [
            "stars",
            "pace"
          ],
          "type": "string",
          "default": "stars"
        },
        "kind": {
          "enum": [
            "server",
            "client",
            "product",
            "skill",
            "plugin",
            "rules",
            "eval"
          ],
          "type": "string"
        },
        "limit": {
          "type": "integer",
          "default": 10,
          "maximum": 50,
          "minimum": 1
        },
        "category": {
          "type": "string",
          "maxLength": 80
        }
      },
      "additionalProperties": false
    }
    arguments 40 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 bc593942cd0ef987.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/bc593942cd0ef987/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/bc593942cd0ef987/badge.svg)](https://brick.blue/agent/bc593942cd0ef987?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
100%

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.