DEX Screener MCP — DEX price/liquidity/volume data
- ✓Open-source license (MIT)
- ✓Actively maintained (<30d)
- ✓Clear description
- ✓Topics declared
- ✓Documented (README)
claude mcp add mcp-dexscreener -- npx -y @pipeworx/mcp-dexscreener{
"mcpServers": {
"mcp-dexscreener": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-dexscreener"]
}
}
}MCP Servers overview
# @pipeworx/dexscreener
DEX Screener MCP — real-time DEX prices and liquidity across all major EVM + Solana chains. No auth.
Part of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1683+ live data sources.
## Tools
- `get_pair(chain, pair_address)` — single pair detail (price, liquidity, volume, txns)
- `get_token(chain, token_address)` — all pairs for a token on one chain
- `search_pairs(query)` — free-text search across pairs (max 30 results)
- `latest_token_profiles()` — newest tokens listed
- `latest_boosted_tokens()` — tokens currently being promoted on DEX Screener
- `token_boosts_top(chain?, token?)` — leaderboard of most-boosted tokens
## Data source
`https://api.dexscreener.com/` — JSON. Rate-limit ~300 req/min per IP.
Endpoints used, because two of the obvious-looking ones are wrong (fleet #1579,
verified against the live API 2026-09-08):
| Tool | Route | Note |
|---|---|---|
| `get_pair` | `/latest/dex/pairs/{chain}/{pair}` | |
| `get_token` | `/token-pairs/v1/{chain}/{token}` | **not** `/tokens/v1/{chain}/{token}` — that route answers 200 with a SINGLE pool (WETH: 1 vs 30), so the wrong one loses 97% of the data without erroring |
| `search_pairs` | `/latest/dex/search?q=` | |
| `latest_token_profiles` | `/token-profiles/latest/v1` | bare array |
| `latest_boosted_tokens` | `/token-boosts/latest/v1` | bare array |
| `token_boosts_top` | `/token-boosts/top/v1` | takes no path filter; `chain`/`token` are filtered client-side |
## What an empty answer means here
DEX Screener signals "nothing indexed" with **HTTP 200 and an empty list** —
`[]` from the `v1` routes, `{"pairs":null}` from `/latest/dex/pairs`. It does
not 404 for an unknown address. So this pack only ever says `not_found:` on a
200 it actually read; any error status is reported as `upstream_down:` and
explicitly says it is NOT evidence about the caller's arguments. Before #1579
the pack mapped every 404 to "no pairs for that address, check the chain and
the exact contract address" — which was false for every `get_token` call it
ever served, and convincing enough that callers re-checked correct addresses.
Common chain ids: `ethereum`, `solana`, `bsc`, `polygon`, `arbitrum`, `base`, `avalanche`, `optimism`, `fantom`.
## Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
```json
{
"mcpServers": {
"dexscreener": {
"url": "https://gateway.pipeworx.io/dexscreener/mcp"
}
}
}
```
### What this endpoint actually serves
`tools/list` at `https://gateway.pipeworx.io/dexscreener/mcp` returns the tools in the table
above **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,
`discover_tools`, `search_within`, `remember`/`recall` and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's `initialize` response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
`ask_pipeworx`, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed
directly, instead of just this one's:
```json
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
```
Both URLs reach the same gateway and the same 1683+ data sources. The
only difference is which pack's tools are listed **directly**; `ask_pipeworx`
reaches all of them from either one.
## No MCP client? Call it over HTTP
```bash
curl -X POST https://gateway.pipeworx.io/v1/tools/dexscreener_get_pair \
-H 'Content-Type: application/json' \
-d '{"chain":"ethereum","pair_address":"0x88e6a0c2ddd26feeb64f039a2c41296fcb3f5640"}'
```
No account needed for the first calls. Inspect any tool: `GET https://gateway.pipeworx.io/v1/tools/dexscreener_get_pair`. Find one: `POST https://gateway.pipeworx.io/v1/tools/search_packs` with `{"query":"..."}`.
## Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no
gateway round-trip:
```json
{
"mcpServers": {
"dexscreener": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-dexscreener"]
}
}
}
```
Or run it directly to confirm it starts:
```bash
npx -y @pipeworx/mcp-dexscreener
```
It speaks MCP over stdin/stdout and answers `initialize`/`tools/list`/`tools/call`
for **only** this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
## Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English —
this works on the pack endpoint above as well as on the full gateway:
```
ask_pipeworx({ question: "your question about Dexscreener data" })
```
The gateway picks the right tool and fills the arguments automatically.
## More
- [Docs and guides](https://pipeworx.io/docs)
- [pipeworx.io](https://pipeworx.io)
## License
MIT
What people ask about mcp-dexscreener
What is pipeworx-io/mcp-dexscreener?
+
pipeworx-io/mcp-dexscreener is mcp servers for the Claude AI ecosystem. DEX Screener MCP — DEX price/liquidity/volume data It has 0 GitHub stars and its last recorded update is dated 2026-09-25.
How do I install mcp-dexscreener?
+
You can install mcp-dexscreener by cloning the repository (https://github.com/pipeworx-io/mcp-dexscreener) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is pipeworx-io/mcp-dexscreener safe to use?
+
Our security agent has analyzed pipeworx-io/mcp-dexscreener and assigned a Trust Score of 95/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains pipeworx-io/mcp-dexscreener?
+
pipeworx-io/mcp-dexscreener is maintained by pipeworx-io. The last recorded GitHub activity is dated 2026-09-25, with 0 open issues.
Are there alternatives to mcp-dexscreener?
+
Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.
Deploy mcp-dexscreener to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/pipeworx-io-mcp-dexscreener)<a href="https://claudewave.com/repo/pipeworx-io-mcp-dexscreener"><img src="https://claudewave.com/api/badge/pipeworx-io-mcp-dexscreener" alt="Featured on ClaudeWave: pipeworx-io/mcp-dexscreener" width="320" height="64" /></a>More MCP Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
An open-source AI agent that brings the power of Gemini directly into your terminal.
Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
🕷️ An adaptive Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https://x.com/Scrapling_dev
The fastest path to AI-powered full stack observability, even for lean teams.