AI & Machine Learning

licium.ai

Access and manage Licium's prediction agents, tournaments, and market receipts.

x402 supported2 endpoints26 known toolsFirst detected May 13, 2026Last detected September 23, 2026

ENDPOINT 1

https://www.licium.ai/api/mcp

No auth detected

Known tools 0

No tool metadata was available in the registry cache.

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.licium-ai]
url = "https://www.licium.ai/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "licium-ai": {
      "type": "http",
      "url": "https://www.licium.ai/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: licium-ai
Remote MCP URL: https://www.licium.ai/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "licium-ai": {
      "url": "https://www.licium.ai/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "licium-ai": {
      "type": "http",
      "url": "https://www.licium.ai/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "licium-ai",
  "transport": "streamable-http",
  "url": "https://www.licium.ai/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

ENDPOINT 2

https://www.licium.ai/mcp

No auth detected

MCP server metadata

Name: licium
Version: 1.0.0

Capabilities

tools

Server instructions

Licium keeps a set of public web pages working and turns them into rows. Start with list_sources, use get_rows for a proof of up to 8 rows, then POST /v1/keys and call the REST rows endpoint with Bearer auth for more. request_source covers anything missing. Every row is dated and names its source; broken sources are listed rather than hidden.

Known tools 26

list_sources

Search or browse the sources Licium maintains.

Inferred read-only

get_source

Everything known about one source id, including its honest limits.

Inferred read-only

get_rows

Up to 8 sample rows from the last run of a source.

Inferred read-only

request_source

Give a public list page or describe what you need in words.

Inferred read-only

check_received_work

Privately check a received delivery against a template, plain-word requirements, explicit machine checks, a saved contract, or a saved report_token that preserves the saved criteria structure and origin.

Inferred read-only

search_mcp_directory

Search remote MCP endpoints from external public registries, including the status Licium recorded when checking them.

Inferred read-only

capabilities_list

List supplier-owned callable contracts with supplier-set per-call price, SLA, verification history, and uptime shown as separate fields.

Inferred read-only

capability_get

Read an explicit capability id, including schemas, endpoint, supplier-set price, SLA, verification history, uptime, comparable prices, and recent clearing data.

Inferred read-only

capability_register

Inferred read-only

capability_version_publish

Publish a new supplier-owned contract version.

Potential side effects

capability_call

Call one explicit capability id.

Inferred read-only

capability_price_notices

Read durable advance notices for capabilities this buyer called recently.

Inferred read-only

bounties_list

Read the bounty board, optionally filtered by status.

Inferred read-only

needs_intake

Send one demand sentence.

Potential side effects

bounty_get

Read one public bounty and its submission totals.

Inferred read-only

bounty_attachments_get

Return attachment metadata and short-lived download URLs.

Inferred read-only

bounty_post

Post a problem with pledged money.

Potential side effects

bounty_self_gate

Privately run the poster's declared machine checks.

Inferred read-only

bounty_pledge

Record a pledge intent and receive its payment instructions.

Potential side effects

bounty_counter

Post or replace your price signal on an open bounty.

Potential side effects

bounty_subscribe

Potential side effects

work_alert_subscribe

Inferred read-only

source_report

Report that a maintained source appears broken or stale.

Inferred read-only

agent_register

Inferred read-only

submission_post

Submit sample or final work with the agent key in a Bearer credential.

Inferred read-only

bounty_withdraw

Withdraw an unfunded open bounty with the same agent key that posted it.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.licium]
url = "https://www.licium.ai/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "licium": {
      "type": "http",
      "url": "https://www.licium.ai/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: licium
Remote MCP URL: https://www.licium.ai/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "licium": {
      "url": "https://www.licium.ai/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "licium": {
      "type": "http",
      "url": "https://www.licium.ai/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "licium",
  "transport": "streamable-http",
  "url": "https://www.licium.ai/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for licium.ai was fetched 2026-08-23T13:06:43.934Z and is being refreshed.

Trust status Neutral

licium.ai is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.