edgeful API: 150+ trading probability reports

the edgeful MCP server makes reports available directly in your AI conversation. read the existing catalog, or enable custom report writes to build, revise, run, and save your own reports. no local project or .env file is required for a native connector.

this is a different setup path from set up API with your AI agent, which wires the REST API into a local codebase. use MCP when you want edgeful available directly inside your chat client; use the API path when you’re building something that calls edgeful from your own code.

server URL: https://api.edgeful.com/mcp

Claude (Desktop or Web)

add the connector

in Claude, go to Settings → Connectors → Add custom connector.

point it at edgeful

name it edgeful and set the URL to https://api.edgeful.com/mcp, then save.

connect

click Connect. a browser window opens an edgeful sign-in and consent screen, not a bare API key prompt. sign in with your edgeful account and click Allow.

ask a question

back in Claude, the edgeful tools are available in the conversation. try something like “what are the top reports for ES right now?” and watch it make a tool call.

Codex (via ChatGPT desktop app) / Codex CLI

add the server

app (ChatGPT desktop): open ⚙️ Settings → Plugins (under Integrations) → Add → Add MCP server. in the “Connect to a custom MCP” form, name it edgeful, set type to Streamable HTTP, and set the URL to https://api.edgeful.com/mcp. leave bearer token and headers empty, then save.CLI: the same config is shared through ~/.codex/config.toml, so entries added in the app show up there too.

authenticate

the server shows up flagged as requiring OAuth. click Authenticate, sign in with your edgeful account in the browser tab that opens, and click Allow. in the CLI, run codex mcp login edgeful if it asks you to reauth.

use it

restart if Codex asks you to, then the edgeful tools are available in a thread. /mcp in the composer lists active servers.

clients without a native OAuth connector (Cursor, older setups)

some MCP clients can’t run the OAuth handshake yet and only support a static bearer token. for those, keep using an edgeful API key over mcp-remote, the same setup this replaces for Claude and Codex:

generate a key in the API dashboard → API Keys (see authentication for the full key format and rotation flow).
add this to your client’s MCP config:

mcp config

{
  "mcpServers": {
    "edgeful": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.edgeful.com/mcp",
        "--header",
        "Authorization: Bearer ${EDGEFUL_API_KEY}"
      ]
    }
  }
}

set EDGEFUL_API_KEY in your environment (never paste the key directly into a shared config file).

plan access

MCP calls are entitlement-gated the same way the REST API is: your edgeful account needs an active API-enabled plan (Essential, Pro, or All Access). signing in works for any account, but a tool call from an account without an API-enabled plan returns a missing_entitlement error. see authentication for the full plan breakdown.

build and save custom reports

in the API dashboard, enable connected Claude under build custom reports with Claude. this permission applies to connections signed in to your account. if your client uses an API key instead, enable this API key. both permissions start off; new and regenerated keys are read-only. then ask Claude to build a report, review its methodology and sample, and tell it to save. the report appears under my custom reports in Edgeful AI, marked built via API. you can complete the whole conversation in Claude. Edgeful generates and validates the report code. builds and revisions use your Edgeful AI allowance. runs use the saved code without a model call. turning writes off keeps reading available. see build and save a custom report for the complete workflow and limits.

available tools

tool	purpose	write permission
`list_allowed_report_endpoints`	discover standard reports	no
`describe_report_endpoint`	read a standard report’s parameters	no
`call_report_endpoint`	fetch a standard report	no
`get_discovery_scan`	find reports for a ticker	no
`build_custom_report`	build from a brief or return a clarifying question	yes
`revise_custom_report`	answer a clarification or revise the draft	yes
`run_custom_report`	run a draft or saved report with selected inputs	yes
`save_custom_report`	publish a reviewed draft to my custom reports	yes
`list_custom_reports`	list your saved reports	no
`get_custom_report_latest_result`	read the latest stored result without running	no
`delete_custom_report`	delete a saved report	yes

works with

Claude Desktop, Claude Web, Codex (via ChatGPT desktop app or Codex CLI), Cursor, and any MCP client that speaks Streamable HTTP.

getting started

skills

API guides

API Reference

set up MCP with your AI agent

Claude (Desktop or Web)

Codex (via ChatGPT desktop app) / Codex CLI

clients without a native OAuth connector (Cursor, older setups)

plan access

build and save custom reports

available tools

works with

​Claude (Desktop or Web)

​Codex (via ChatGPT desktop app) / Codex CLI

​clients without a native OAuth connector (Cursor, older setups)

​plan access

​build and save custom reports

​available tools

​works with

Claude (Desktop or Web)

Codex (via ChatGPT desktop app) / Codex CLI

clients without a native OAuth connector (Cursor, older setups)

plan access

build and save custom reports

available tools

works with