by heurist-network
Enables Claude and other MCP‑compatible interfaces to query a rich set of blockchain, crypto market, and web3 tools through the Heurist Mesh API, supporting both SSE and stdio transports.
Provides a Model Context Protocol (MCP) server that bridges Claude (or any MCP‑compatible client) to the Heurist Mesh ecosystem—an open network of specialized AI agents for blockchain data analysis, token security, market metrics, and more. The server aggregates tools from agents such as CoinGecko, DexScreener, Elfa Twitter Intelligence, Exa Search, Firecrawl, and GoPlus, exposing them via simple RPC calls.
uv pip install -e .
or build the Docker image docker build -t mesh-tool-server .
.uv run mesh-tool-server
) or Docker with -e TRANSPORT=stdio
and configure claude_desktop_config.json
.HEURIST_API_KEY
in .env
, then start with uv run mesh-tool-server --transport sse --port 8000
or docker run -p 8000:8000 mesh-tool-server
and point the client to http://<host>:8000/sse
.get_coingecko_id
, search_mentions
, fetch_security_details
) with required parameters as described in the README.server.py
’s DEFAULT_AGENTS
.Q: Which transport should I use? A: Use SSE for web‑based clients like Cursor; use stdio for Claude Desktop or any local MCP client.
Q: Do I need separate API keys for each tool? A: No, a single Heurist API key grants access to all integrated agents.
Q: Can I add new agents?
A: Yes. Edit the DEFAULT_AGENTS
list in server.py
and include any agent listed in the Heurist metadata.
Q: Is there a hosted version? A: A shared SSE endpoint is available at https://sequencer-v2.heurist.xyz/mcp/sse, but performance may vary.
Q: How do I run the server in Docker with custom environment variables?
A: Pass them with -e
, e.g., docker run -p 8000:8000 -e HEURIST_API_KEY=YOUR_KEY mesh-tool-server
.
A Model Context Protocol (MCP) server that connects to Heurist Mesh APIs, providing Claude with access to various blockchain and web3 tools.
Heurist Mesh is an open network of purpose-built AI agents and tools, each specialized in particular web3 domains such as blockchain data analysis, smart contract security, token metrics, and blockchain interaction. We are actively growing the Heurist Mesh ecosystem, continuously integrating more tools to expand its capabilities.
You can use Heurist Mesh MCP Portal to create SSE MCP Servers. Select your agents and compose a personalized swarm for your tasks!
We provide a hosted SSE endpoint at https://sequencer-v2.heurist.xyz/mcp/sse. This includes all the tools from the following commonly used agents: CoingeckoTokenInfoAgent
, ElfaTwitterIntelligenceAgent
, ExaSearchAgent
, DexScreenerTokenInfoAgent
, ZerionWalletAnalysisAgent
. This is a shared server and the performance may be unstable.
Cursor can directly access SSE servers. For Claude Desktop users, we recommend installing mcp-proxy to connect to the SSE server.
# Clone the repository
git clone https://github.com/heurist-network/heurist-mesh-mcp-server.git
cd heurist-mesh-mcp-server
# Install the package
uv pip install -e .
# Clone the repository
git clone https://github.com/heurist-network/heurist-mesh-mcp-server.git
cd heurist-mesh-mcp-server
# Build the Docker image
docker build -t mesh-tool-server .
To use this with Claude Desktop, add the following to your claude_desktop_config.json
:
{
"mcpServers": {
"heurist-mesh-agent": {
"command": "uv",
"args": [
"--directory",
"/path/to/heurist-mesh-mcp-server/mesh_mcp_server", // Update this path
"run",
"mesh-tool-server"
],
"env": {
"HEURIST_API_KEY": "your-api-key-here" // Update this key
}
}
}
}
Alternatively, you can use Docker with Claude Desktop by adding this to your claude_desktop_config.json
:
{
"mcpServers": {
"mesh-agent": {
"command": "docker",
"args": [
"run",
"--rm",
"-i",
"-e", "TRANSPORT=stdio",
"-e", "HEURIST_API_KEY=your-api-key-here", // Update this key
"mesh-tool-server"
]
}
}
}
Replace /path/to/heurist-mesh-mcp-server
with the actual path to the repository and your-api-key-here
with your Heurist API key.
.env
cp .env.example .env
HEURIST_API_KEY=your-api-key-here
uv run mesh-tool-server --transport sse --port 8000
docker run -p 8000:8000 -e PORT=8000 mesh-tool-server
Then, in Cursor, add the MCP Server URL: http://0.0.0.0:8000/sse
Visit https://mesh.heurist.ai/metadata.json or https://mcp.heurist.ai/ to view all available tools.
Tool Name | Description | Agent | Parameters | Required Params |
---|---|---|---|---|
get_coingecko_id | Search for a token by name to get its CoinGecko ID | CoinGeckoTokenInfoAgent | token_name (string): The token name to search for | token_name |
get_token_info | Get detailed token information and market data using CoinGecko ID (you can't use the token address or name or symbol) | CoinGeckoTokenInfoAgent | coingecko_id (string): The CoinGecko ID of the token | coingecko_id |
get_trending_coins | Get the current top trending cryptocurrencies on CoinGecko | CoinGeckoTokenInfoAgent | - | None |
get_specific_pair_info | Get trading pair info by chain and pair address on DexScreener | DexScreenerTokenInfoAgent | chain (string): Chain identifier (e.g., solana, bsc, ethereum, base)pair_address (string): The pair contract address to look up | chain, pair_address |
get_token_pairs | Get the trading pairs by chain and token address on DexScreener | DexScreenerTokenInfoAgent | chain (string): Chain identifier (e.g., solana, bsc, ethereum, base)token_address (string): The token contract address to look up all pairs for | chain, token_address |
get_token_profiles | Get the basic info of the latest tokens from DexScreener | DexScreenerTokenInfoAgent | - | None |
search_pairs | Search for trading pairs on DexScreener by token name, symbol, or address | DexScreenerTokenInfoAgent | search_term (string): Search term (token name, symbol, or address) | search_term |
get_trending_tokens | Get current trending tokens on Twitter | ElfaTwitterIntelligenceAgent | time_window (string): Time window to analyze | None |
search_account | Analyze a Twitter account with both mention search and account stats | ElfaTwitterIntelligenceAgent | username (string): Twitter username to analyze (without @)days_ago (integer): Number of days to look back for mentionslimit (integer): Maximum number of mention results | username |
search_mentions | Search for mentions of specific tokens or topics on Twitter | ElfaTwitterIntelligenceAgent | keywords (array): List of keywords to search fordays_ago (integer): Number of days to look backlimit (integer): Maximum number of results (minimum: 20) | keywords |
answer | Get a direct answer to a question using Exa's answer API | ExaSearchAgent | question (string): The question to answer | question |
search | Search for webpages related to a query | ExaSearchAgent | search_term (string): The search termlimit (integer): Maximum number of results to return (default: 10) | search_term |
search_and_answer | Perform both search and answer operations for a query | ExaSearchAgent | topic (string): The topic to search for and answer | topic |
execute_search | Execute a web search query by reading the web pages | FirecrawlSearchAgent | search_term (string): The search term to execute | search_term |
generate_queries | Generate related search queries for a topic that can expand the research | FirecrawlSearchAgent | topic (string): The main topic to researchnum_queries (integer): Number of queries to generate | topic |
fetch_security_details | Fetch security details of a blockchain token contract | GoplusAnalysisAgent | contract_address (string): The token contract addresschain_id (['integer', 'string']): The blockchain chain ID or 'solana' for Solana tokens. Supported chains: Ethereum (1), Optimism (10), Cronos (25), BSC (56), Gnosis (100), HECO (128), Polygon (137), Fantom (250), KCC (321), zkSync Era (324), ETHW (10001), FON (201022), Arbitrum (42161), Avalanche (43114), Linea Mainnet (59144), Base (8453), Tron (tron), Scroll (534352), opBNB (204), Mantle (5000), ZKFair (42766), Blast (81457), Manta Pacific (169), Berachain Artio Testnet (80085), Merlin (4200), Bitlayer Mainnet (200901), zkLink Nova (810180), X Layer Mainnet (196), Solana (solana) | contract_address |
The server comes with a default set of agents. To modify which agents are available:
server.py
file and locate the Config
class.DEFAULT_AGENTS
list to add or remove agents listed at Heurist MetadataDEFAULT_AGENTS = [
"CoinGeckoTokenInfoAgent",
"DexScreenerTokenInfoAgent",
"ElfaTwitterIntelligenceAgent",
"ExaSearchAgent",
"FirecrawlSearchAgent",
"GoplusAnalysisAgent",
# Add agents here
"NewAgent"
]
This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License.
Please log in to share your review and rating for this MCP.
Explore related MCPs that share similar capabilities and solve comparable challenges
by modelcontextprotocol
An MCP server implementation that provides a tool for dynamic and reflective problem-solving through a structured thinking process.
by danny-avila
Provides a self‑hosted ChatGPT‑style interface supporting numerous AI models, agents, code interpreter, image generation, multimodal interactions, and secure multi‑user authentication.
by block
Automates engineering tasks on local machines, executing code, building projects, debugging, orchestrating workflows, and interacting with external APIs using any LLM.
by RooCodeInc
Provides an autonomous AI coding partner inside the editor that can understand natural language, manipulate files, run commands, browse the web, and be customized via modes and instructions.
by pydantic
A Python framework that enables seamless integration of Pydantic validation with large language models, providing type‑safe agent construction, dependency injection, and structured output handling.
by lastmile-ai
Build effective agents using Model Context Protocol and simple, composable workflow patterns.
by mcp-use
A Python SDK that simplifies interaction with MCP servers and enables developers to create custom agents with tool‑calling capabilities.
by nanbingxyz
A cross‑platform desktop AI assistant that connects to major LLM providers, supports a local knowledge base, and enables tool integration via MCP servers.
by gptme
Provides a personal AI assistant that runs directly in the terminal, capable of executing code, manipulating files, browsing the web, using vision, and interfacing with various LLM providers.