SwogeAgentic
Crypto intel for AI agents: token scans, SWOGE AI colony data, OSINT, web search, images, video
Should I use this
Quality & Safety
Findings (3)
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domainin scan_token
- MEDIUMTool description contains URL to non-standard domainin new_launches
Based on automated analysis of tool definitions and protocol compliance.
Context Cost
This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.
Install
One-Click Install
Add this to your `claude_desktop_config.json` file:
{
"mcpServers": {
"swogeagentic": {
"url": "https://web-production-220a3.up.railway.app/mcp"
}
}
}Remote endpoints
https://web-production-220a3.up.railway.app/mcpstreamable-httpWhat it can do
Tool inventory
Tools (11)
🟢scan_token(address, quote)
Use this before buying, listing or writing about an EVM token, to check its market and its contract in one call (contract security Powered by Go+ Security, https://gopluslabs.io). Give the contract address (0x…), on any chain DexScreener indexes. Returns the deepest pool (price, liquidity, market cap, 24 h volume and change, from DexScreener), the GoPlus contract checks where GoPlus covers the chain (honeypot, buy and sell tax, mint, pause, blacklist, hidden owner, holder concentration) and, for Robinhood Chain tokens, the average 30-minute move the SWOGE AI colony measured on past tokens sharing each trait, with its number of observations, plus a shareable scan card. Measurements, never a buy or sell signal; unknown stays unknown.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "EVM contract address, 0x followed by 40 hex characters"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"address"
]
}🟢colony_activity(token, quote)
Use this when you want to know what the SWOGE AI colony, an autonomous paper-trading colony on Robinhood Chain, holds or did recently, overall or on one token. Returns its open positions, latest buys and sells with results and reasons, its paper ledger (trades, average result, share of winners) and the record of the mirror that repeats some trades with real money. Optionally filtered to one token symbol or address. Paper trades are measurements, never advice.
Input Schema
{
"type": "object",
"properties": {
"token": {
"type": "string",
"description": "optional token symbol (e.g. TELEPAD) or address to filter on"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
}
}🟢swoge_economy(quote)
Use this when you need the current state of the $SWOGE token economy. Returns total supply, the amount burned and the casino vault balance (each with its share of supply), the staking APR and cap, read on-chain on Robinhood Chain, and the $SWOGE price in USD from DexScreener.
Input Schema
{
"type": "object",
"properties": {
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
}
}🟢new_launches(limit, quote)
Use this when you want the newest tokens on Robinhood Chain, minutes after their pool opens, with what an autonomous trading colony decided about each. Returns up to 30 fresh tokens (age, pool size, market cap, 5-minute move, score, and why the SWOGE AI colony did or did not buy it) and the older tokens it keeps watching with its verdict on each. Its contract checks use GoPlus data: Powered by Go+ Security (https://gopluslabs.io). Live reads, never advice.
Input Schema
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 30,
"description": "how many fresh tokens (default 15)"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
}
}🟢wallet_intel(address, quote)
Use this when you need to know who is behind an EVM address, typically a token deployer, before trusting what it launches. Returns findings first (such as repeat launching), then facts: the tokens it deployed on the launchpads the colony indexes and what the SWOGE AI colony measured on launchers like it (with observation counts), each with its source. Passive: the address is never contacted.
Input Schema
{
"type": "object",
"properties": {
"address": {
"type": "string",
"description": "EVM address, 0x followed by 40 hex characters"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"address"
]
}🟢osint_lookup(target, quote)
Use this when you need passive reconnaissance on internet infrastructure: a domain, an IP address, a website URL, an autonomous system (AS15169) or a CVE id. Returns findings first, then DNS, certificate, registration, hosting and exposure facts, each with its source. Passive only; people (e-mails, usernames, phone numbers, names) are refused.
Input Schema
{
"type": "object",
"properties": {
"target": {
"type": "string",
"description": "a domain, IP, URL, AS number or CVE id"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"target"
]
}🟢web_search(query, quote)
Use this when the answer is outside SWOGE data: news, projects, teams, people, anything on the open web. Returns ranked results with title, URL, date and an extract (Perplexity Search).
Input Schema
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "the search query, as you would type it"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"query"
]
}🟢ask_agent(task, model, quote)
Use this when a question needs several of these tools chained together and a written answer, for example comparing tokens or researching a launcher. SwogeAgentic, a Claude agent, picks the tools, reads the numbers and answers in Markdown with its sources and sample sizes. API key only: billed at its real cost, up to the quoted maximum ("quote": true gives it). Takes 10 to 60 seconds.
Input Schema
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "what you want researched, in any language"
},
"model": {
"type": "string",
"enum": [
"opus-5-5",
"fable-5-1",
"sonnet-5",
"haiku-4-5"
],
"description": "optional Claude model (default sonnet-5)"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"task"
]
}🟢generate_image(prompt, provider, quality, aspect_ratio, count, ...)
Use this when you need an image: an illustration, a meme, a post visual, or the SWOGE character (a prompt that names SWOGE is drawn from the official character). Made with Grok Imagine (default) or ChatGPT Image, speed or quality, 1, 2 or 4 images. Returns image URLs. With an API key: billed at its real cost, up to the quoted maximum. Without a key (x402): a fixed price for that exact request, quoted in the 402.
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "what to draw, in any language"
},
"provider": {
"type": "string",
"enum": [
"grok",
"openai"
],
"description": "grok (Grok Imagine, default) or openai (ChatGPT Image)"
},
"quality": {
"type": "string",
"enum": [
"speed",
"quality"
],
"description": "speed (cheaper) or quality (default)"
},
"aspect_ratio": {
"type": "string",
"enum": [
"auto",
"1:1",
"16:9",
"9:16",
"4:3",
"3:4",
"3:2",
"2:3"
],
"description": "image shape (default auto)"
},
"count": {
"type": "integer",
"enum": [
1,
2,
4
],
"description": "how many images (default 1)"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"prompt"
]
}🟢generate_video(prompt, quality, duration, resolution, aspect_ratio, ...)
Use this when you need a short video clip, 6 or 10 seconds, made with Grok Imagine. Returns a video id at once; poll it with video_status (free) until it is done and gives its URL. API key only: billed at its real cost when the video arrives, up to the quoted maximum, nothing if it fails.
Input Schema
{
"type": "object",
"properties": {
"prompt": {
"type": "string",
"description": "what happens in the video, in any language"
},
"quality": {
"type": "string",
"enum": [
"speed",
"quality"
],
"description": "speed (default) or quality (Grok Imagine Video 1.5)"
},
"duration": {
"type": "integer",
"enum": [
6,
10
],
"description": "seconds (default 6)"
},
"resolution": {
"type": "string",
"enum": [
"480p",
"720p"
],
"description": "default 480p"
},
"aspect_ratio": {
"type": "string",
"enum": [
"auto",
"16:9",
"9:16",
"1:1"
],
"description": "video shape (default auto)"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"prompt"
]
}🟢video_status(id, quote)
Use this when you started a video with generate_video and want to know whether it is ready. Returns pending, done with its URL, or failed and not charged, plus what was billed. Free.
Input Schema
{
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "the id returned by generate_video"
},
"quote": {
"type": "boolean",
"description": "true: return the price of this call without running or paying for it"
}
},
"required": [
"id"
]
}Community
Evidence