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

cdphub

https://cdphub.com

Registry code: 817d3dfd431f7ba8

api record

CdpHub (cdphub.com) is an independent directory of customer data platform (CDP) integrations: the public integration catalogs of every CDP it tracks, in one graph, each listing linked to the page it came from. Use get_tool for one tool (which CDPs list it and which way data flows), check_stack for two to ten tools together, compare_cdps for two CDPs, get_cdp for one CDP's catalog, list_cdps for every CDP, and search_directory for keyword, category or direction searches. The figures count each CDP once per tool. A CDP with no listing for a tool doesn't document one, which is not proof the two…

endpoint
https://cdphub.com/functions/mcp
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 cdphub live?
Yes — it answered the hub's last check (checked 1h ago). It answered 100% of checks over the last 30 days.
Is cdphub free to use?
Yes — the hub reached it with no key and no payment.
What tools does cdphub have?
6 tools: get_tool, compare_cdps, get_cdp, search_directory, check_stack, list_cdps.
Is cdphub 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
385ms

last good check

priced tools
0

of 6 tools

_ answered our checks, 90 days 1 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 6 tools
1 open 5 never probed 1 of 6 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_cdps open 1h ago

    List every customer data platform in CdpHub's directory with its number of tools and listings and its page on cdphub.com, largest catalog first, with the directory's totals.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_tool unknown never probed

    Look up one marketing or data tool (for example Snowflake, Braze, Google Ads or The Trade Desk) in CdpHub's directory: how many of the customer data platforms (CDPs) it tracks list an integration with it, each CDP counted once (both sends data to it and reads from it, only sends, only reads), which CDPs list it in each group and which don't, every listing with its direction, how it runs (server-side, client-side, in the warehouse) and a link to the CDP's own documentation, and the tool's page on cdphub.com. Use it for any question about one tool.

    mcp-tool

    {
      "type": "object",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "The tool, for example \"Snowflake\" or \"Google Ads\"."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • compare_cdps unknown never probed

    Compare two CDPs' integration catalogs in CdpHub's directory, tool by tool: how many tools both list, how many only one does, the most widely listed tools in both, each side's largest categories of tools the other lacks, and the link to their comparison page on cdphub.com.

    mcp-tool

    {
      "type": "object",
      "required": [
        "a",
        "b"
      ],
      "properties": {
        "a": {
          "type": "string",
          "description": "The first CDP, for example \"Segment\"."
        },
        "b": {
          "type": "string",
          "description": "The second CDP, for example \"mParticle\"."
        }
      },
      "additionalProperties": false
    }
    arguments 18 lines
  • get_cdp unknown never probed

    Look up one customer data platform's integration catalog in CdpHub's directory: its number of tools and listings and its rank by catalog size, which way its integrations run, its largest categories with their most widely listed tools, how it connects to the main data warehouses, the CDPs that list the most of the same tools, and its page on cdphub.com.

    mcp-tool

    {
      "type": "object",
      "required": [
        "name"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "The CDP, for example \"Segment\", \"Braze\" or \"Adobe Experience Platform\"."
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • search_directory unknown 1h ago

    Search CdpHub's directory of CDP integrations by keyword, CDP, category, direction or how the integration runs. Returns the exact totals, the first results and the link to the same search on cdphub.com. Use get_tool for one named tool and check_stack for several.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "cdps": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Only these CDPs, for example [\"Tealium\"]."
        },
        "runs": {
          "type": "array",
          "items": {
            "enum": [
              "server",
              "client",
              "warehouse",
              "none"
            ],
            "type": "string"
          },
          "description": "How the integration runs: server-side, client-side, through a warehouse, or \"none\" when the listing doesn't say."
        },
        "sort": {
          "enum": [
            "relevance",
            "coverage",
            "az",
            "added",
            "recommended"
          ],
          "type": "string",
          "description": "The result order. Leave it out to let the directory decide."
        },
        "group": {
          "enum": [
            "tool",
            "listing"
          ],
          "type": "string",
          "description": "Group the results by tool or by listing. Leave it out to let the directory decide."
        },
        "query": {
          "type": "string",
          "description": "Words to search for in tool, listing and CDP names, categories and descriptions, for example \"reverse etl\"."
        },
        "categories": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Only these categories, for example [\"Advertising\"]."
        },
        "directions": {
          "type": "array",
          "items": {
            "enum": [
              "out",
              "into",
              "both",
              "unknown"
            ],
            "type": "string"
          },
          "description": "Which way data moves, from the CDP's side: \"out\" sends data to the tool, \"into\" reads from it, \"both\", or \"unknown\" when the listing doesn't say."
        }
      },
      "additionalProperties": false
    }
    arguments 69 lines
  • check_stack unknown 1h ago

    Check a stack of two to ten tools against every CDP in CdpHub's directory, as the stack check on cdphub.com does: how many CDPs list all of them and which, those CDPs grouped by how they connect to each tool with each group counted, the CDPs that miss exactly one tool grouped by the tool they miss, and a link to the same check on cdphub.com. Use it for any question about two or more tools together, such as which CDPs fit a company's stack.

    mcp-tool

    {
      "type": "object",
      "required": [
        "tools"
      ],
      "properties": {
        "tools": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "maxItems": 10,
          "minItems": 2,
          "description": "The tools, for example [\"Shopify\", \"Klaviyo\", \"Snowflake\"]: two to ten."
        }
      },
      "additionalProperties": false
    }
    arguments 18 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 817d3dfd431f7ba8.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/817d3dfd431f7ba8/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/817d3dfd431f7ba8/badge.svg)](https://brick.blue/agent/817d3dfd431f7ba8?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.