Skip to main content
Glama
ymylive
by ymylive

list_latest_dex_tokens

Retrieve tokens with completed DexScreener profiles — description, website, socials — as an early feed of newly launched, promoted tokens. Verify prices via pair data before using.

Instructions

List the latest tokens that have set up a profile on DexScreener.

A profile means the project has filled in description / website / socials on DexScreener — typically a sign of a newly-launched but at least somewhat promoted token. Useful as an early-signal feed for "what's new today?"

NOTE: a profile does not imply legitimacy or liquidity. Cross-check with get_dex_token_pairs(token_address, ...) before quoting prices.

Args: limit: Max tokens to return (the API itself returns up to ~30).

Returns: Array of token-profile objects with chainId, tokenAddress, url, description, icon, and a links array of websites/socials. On API failure returns {"error": "..."}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo

Implementation Reference

  • The async function 'list_latest_dex_tokens' executes the tool logic: calls DexScreener's /token-profiles/latest/v1 API, checks for errors, and returns up to `limit` items. Decorated with @mcp.tool() which registers it as an MCP tool.
    async def list_latest_dex_tokens(limit: int = 20) -> Any:
        """List the latest tokens that have set up a profile on DexScreener.
    
        A profile means the project has filled in description / website / socials
        on DexScreener — typically a sign of a newly-launched but at least somewhat
        promoted token. Useful as an early-signal feed for "what's new today?"
    
        NOTE: a profile does not imply legitimacy or liquidity. Cross-check with
        `get_dex_token_pairs(token_address, ...)` before quoting prices.
    
        Args:
            limit: Max tokens to return (the API itself returns up to ~30).
    
        Returns:
            Array of token-profile objects with `chainId`, `tokenAddress`, `url`,
            `description`, `icon`, and a `links` array of websites/socials.
            On API failure returns `{"error": "..."}`.
        """
        resp = await _http_get(f"{DEXSCREENER_BASE}/token-profiles/latest/v1")
        if is_error(resp):
            return resp
        items = resp if isinstance(resp, list) else []
        return items[: max(0, limit)]
  • The @mcp.tool() decorator on the function registers 'list_latest_dex_tokens' with the FastMCP server as an MCP tool.
    @mcp.tool()
  • The DEXSCREENER_BASE constant defines the API base URL used by list_latest_dex_tokens to construct the full endpoint URL.
    DEXSCREENER_BASE = "https://api.dexscreener.com"
  • The _http_get helper function handles HTTP GET requests, used by list_latest_dex_tokens to fetch data from the DexScreener API.
    async def _http_get(
        url: str,
        params: dict[str, Any] | None = None,
        headers: dict[str, str] | None = None,
    ) -> Any:
        """GET a URL and return JSON, or a structured error dict on failure.
    
        Delegates to the in-process TTL cache so repeated identical requests
        don't re-hit the network. See `coin_mcp.cache` for routing rules.
        """
        from . import cache  # local import to avoid circular dependency at module load
        return await cache.cached_http_get(url, params=params, headers=headers)
  • The docstring/Args section defines the input schema (limit: int = 20) and the return schema (array of token-profile objects).
    Args:
        limit: Max tokens to return (the API itself returns up to ~30).
    
    Returns:
        Array of token-profile objects with `chainId`, `tokenAddress`, `url`,
        `description`, `icon`, and a `links` array of websites/socials.
        On API failure returns `{"error": "..."}`.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes return type, error handling, and API cap. No destructive behavior implied, though annotations absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-organized with purpose, caveats, and structured Args/Returns sections. Efficient and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers all necessary context: purpose, usage, limitations, parameter, and return format. Adequate for invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only parameter 'limit' gets clear explanation of meaning and API cap, compensating for 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb 'list' and specific resource 'latest tokens with profile on DexScreener'. Differentiates from sibling tools like 'dex_search' by focusing on token profiles.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states use case as early-signal feed and warns about legitimacy, suggesting cross-check with 'get_dex_token_pairs'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ymylive/coin-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server