Extcord

endpoint

https://extcord.io/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 Extcord live?

Yes — it answered the hub's last check (checked 59m ago). It answered 100% of checks over the last 30 days.

Is Extcord free to use?

Yes — the hub reached it with no key and no payment.

What tools does Extcord have?

6 tools: invoke, run_pipeline, run_recipe, save_recipe, inspect, discover.

Is Extcord 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.

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.

• discover open 59m ago

  Find out what this server can do. With no arguments: every op by category with a one-line intent, plus saved recipes. With query: the best-matching ops and recipes. With op: that op's full contract and examples.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445

  {
    "type": "object",
    "title": "discoverArguments",
    "properties": {
      "op": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Op",
        "default": null,
        "description": "An op id to get its full contract: args schema, behavior, worked examples."
      },
      "query": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Query",
        "default": null,
        "description": "Words describing what you want to do, e.g. 'html table to rows' or 'days between dates'."
      },
      "accepts": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Accepts",
        "default": null,
        "description": "Only ops that take this input type: text, html, json, list, table, number, boolean."
      }
    }
  }

  arguments 45 lines copy
• invoke unknown 59m ago

  Run one operation and get its result as a handle: type, size, estimated tokens, the value itself if small (else a preview), and suggested next ops. Example: invoke(op="fetch", args={"url": "https://example.com"}), then invoke(op="html_to_text", input="<handle from that result>").

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354

  {
    "type": "object",
    "title": "invokeArguments",
    "required": [
      "op"
    ],
    "properties": {
      "op": {
        "type": "string",
        "title": "Op",
        "description": "Op id, e.g. 'fetch', 'html_to_text', 'calc'. See discover()."
      },
      "args": {
        "anyOf": [
          {
            "type": "object",
            "additionalProperties": true
          },
          {
            "type": "null"
          }
        ],
        "title": "Args",
        "default": null,
        "description": "The op's arguments, e.g. {\"url\": \"https://example.com\"} for fetch or {\"expr\": \"2 ** 10\"} for calc."
      },
      "input": {
        "title": "Input",
        "default": null,
        "description": "The data to operate on: a handle id from an earlier result (h_...), or a literal value (text, number, list, object). Omit for ops that take no input, like fetch, calc or now."
      },
      "input_type": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Input Type",
        "default": null,
        "description": "Override the inferred type of a literal input, e.g. 'html'."
      },
      "inline_max_tokens": {
        "type": "integer",
        "title": "Inline Max Tokens",
        "default": 300,
        "maximum": 20000,
        "minimum": 0,
        "description": "Results up to this many estimated tokens include their value directly; larger ones return a preview. Default 300."
      }
    }
  }

  arguments 54 lines copy
• run_pipeline unknown never probed

  Chain operations in one call; only the final result comes back, intermediate data stays on the server. Example steps: [{"op": "fetch", "args": {"url": "https://example.com/pricing"}, "as": "page"}, {"op": "extract_tables", "input": "$page", "args": {"index": 0}}, {"op": "to_markdown", "input": "$1"}]. Use dry_run=true first when unsure.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445

  {
    "type": "object",
    "title": "run_pipelineArguments",
    "required": [
      "steps"
    ],
    "properties": {
      "steps": {
        "type": "array",
        "items": {
          "type": "object",
          "additionalProperties": true
        },
        "title": "Steps",
        "description": "Ordered steps: {\"op\": id, \"input\"?: ref|handle|value, \"args\"?: {...}, \"as\"?: name}. Refer to earlier steps as \"$0\", \"$1\", \"$name\", or paths like \"$1[0]\"; refs work inside args too."
      },
      "dry_run": {
        "type": "boolean",
        "title": "Dry Run",
        "default": false,
        "description": "Check refs, args, types, cost and side effects without running anything."
      },
      "result_from": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Result From",
        "default": null,
        "description": "Which step to return, as a ref like \"$2\" or \"$prices[0]\". Default: the last step."
      },
      "inline_max_tokens": {
        "type": "integer",
        "title": "Inline Max Tokens",
        "default": 300,
        "maximum": 20000,
        "minimum": 0,
        "description": "Results up to this many estimated tokens include their value directly; larger ones return a preview. Default 300."
      }
    }
  }

  arguments 45 lines copy
• run_recipe unknown never probed

  Run a saved pipeline in one call. Built-ins: page_to_markdown (url, max_tokens), page_outline (url), page_links (url, contains), page_tables (url, index), find_on_page (url, pattern).

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041

  {
    "type": "object",
    "title": "run_recipeArguments",
    "required": [
      "name"
    ],
    "properties": {
      "name": {
        "type": "string",
        "title": "Name",
        "description": "Recipe name, e.g. 'page_to_markdown'. discover() lists them."
      },
      "params": {
        "anyOf": [
          {
            "type": "object",
            "additionalProperties": true
          },
          {
            "type": "null"
          }
        ],
        "title": "Params",
        "default": null,
        "description": "Values for the recipe's params, e.g. {\"url\": \"https://example.com\"}."
      },
      "dry_run": {
        "type": "boolean",
        "title": "Dry Run",
        "default": false
      },
      "inline_max_tokens": {
        "type": "integer",
        "title": "Inline Max Tokens",
        "default": 300,
        "maximum": 20000,
        "minimum": 0,
        "description": "Results up to this many estimated tokens include their value directly; larger ones return a preview. Default 300."
      }
    }
  }

  arguments 41 lines copy
• save_recipe unknown never probed

  Save a working pipeline under a name so any agent can run it later with run_recipe. Saved recipes are shared and can't be overwritten.

  mcp-tool

  123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960

  {
    "type": "object",
    "title": "save_recipeArguments",
    "required": [
      "name",
      "description",
      "steps"
    ],
    "properties": {
      "name": {
        "type": "string",
        "title": "Name",
        "description": "3-64 lowercase letters, digits or underscores, e.g. acme_pro_price."
      },
      "steps": {
        "type": "array",
        "items": {
          "type": "object",
          "additionalProperties": true
        },
        "title": "Steps",
        "description": "Pipeline steps, with values to vary written as {{param}}, e.g. {\"op\": \"fetch\", \"args\": {\"url\": \"{{url}}\"}}."
      },
      "params": {
        "anyOf": [
          {
            "type": "object",
            "additionalProperties": {
              "type": "object",
              "additionalProperties": true
            }
          },
          {
            "type": "null"
          }
        ],
        "title": "Params",
        "default": null,
        "description": "Each {{param}}: {\"type\": \"string\", \"description\": \"...\", \"default\"?: ...}."
      },
      "description": {
        "type": "string",
        "title": "Description",
        "description": "One sentence: what it returns, for other agents searching later."
      },
      "result_from": {
        "anyOf": [
          {
            "type": "string"
          },
          {
            "type": "null"
          }
        ],
        "title": "Result From",
        "default": null,
        "description": "Ref of the step to return; default the last."
      }
    }
  }

  arguments 60 lines copy
• inspect unknown 59m ago

  Look at a handle: its summary, its value one page at a time, or its provenance. Check est_tokens in the summary before reading a big value; it's usually cheaper to narrow it with an op first (find, select, filter, fit).

  mcp-tool

  1234567891011121314151617181920212223242526272829303132333435363738394041424344454647

  {
    "type": "object",
    "title": "inspectArguments",
    "required": [
      "handle"
    ],
    "properties": {
      "view": {
        "enum": [
          "summary",
          "value",
          "provenance"
        ],
        "type": "string",
        "title": "View",
        "default": "summary",
        "description": "summary: size, preview, next ops. value: the data itself, paged. provenance: the chain of ops, args and sources that produced it."
      },
      "limit": {
        "anyOf": [
          {
            "type": "integer",
            "maximum": 100000,
            "minimum": 1
          },
          {
            "type": "null"
          }
        ],
        "title": "Limit",
        "default": null,
        "description": "For view=value: page size (default 4000 chars or 50 items)."
      },
      "handle": {
        "type": "string",
        "title": "Handle",
        "description": "A handle id like h_3f9a1c2b7e."
      },
      "offset": {
        "type": "integer",
        "title": "Offset",
        "default": 0,
        "minimum": 0,
        "description": "For view=value: start position (chars for text, items for lists)."
      }
    }
  }

  arguments 47 lines copy

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

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.