Skip to main content
Glama
kukapay

chainlink-feeds-mcp

by kukapay
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Remote

Chainlink Feeds MCP Server

An MCP server that provides real-time access to Chainlink's decentralized on-chain price feeds, optimized for seamless integration into AI agents and autonomous systems

License Node.js Status

Features

  • Query Latest Price: Fetch the latest price for a specified price feed pair (e.g., FIL/ETH) on a given chain (e.g., ethereum), including price, decimals, round ID, and timestamp.

  • Query Price by Round ID: Retrieve price data for a specific round ID (currently a placeholder due to on-chain historical data limitations).

  • List Supported Chains: Get a comma-separated list of supported blockchain networks (e.g., ethereum,base).

  • List All Feeds: Retrieve a Markdown-formatted list of all chains and their price feed names (e.g., - ethereum: FIL/ETH,FDUSD/USD).

  • List Feeds by Chain: Obtain a comma-separated list of price feed names for a specific chain (e.g., FIL/ETH,FDUSD/USD for ethereum).

  • Configurable Feeds: Define price feeds and RPC endpoints in a feeds.json file, supporting multiple chains and feed categories.

Related MCP server: uniswap-price-mcp

Supported Chains and Feeds

The server supports 9 blockchain networks with a total of 329 price feeds, as defined in feeds.json:

  • Ethereum: 107 feeds (e.g., FIL/ETH, BTC/USD, USDC/USD)

  • BNB Chain (bsc): 80 feeds (e.g., DOT/USD, CAKE/USD, BUSD/BNB)

  • Base: 52 feeds (e.g., AXL/USD, USDC/USD, WIF/USD)

  • Starknet: 9 feeds (e.g., ETH/USD, BTC/USD, WSTETH/ETH)

  • Linea: 15 feeds (e.g., ETH/USD, FOXY/USD, MATIC/USD)

  • Mantle: 6 feeds (e.g., MNT/USD, USDT/USD, BTC/USD)

  • Scroll: 22 feeds (e.g., SCR/USD, STETH/USD, WBTC/BTC)

  • zkSync: 16 feeds (e.g., ZK/USD, PEPE/USD, TRUMP/USD)

  • Celo: 22 feeds (e.g., CELO/USD, CUSD/USD, NGN/USD)

Additional chains and feeds can be added by updating feeds.json with new network configurations and proxy addresses from Chainlink's Price Feeds documentation.

Prerequisites

  • Node.js: Version 18.x or higher.

  • npm: For dependency installation.

  • Infura API Key: Obtain a key from the MetaMask Developer Dashboard with access to supported networks (e.g., Ethereum, Base).

  • MCP Inspector (optional): For testing the server locally.

  • Claude Desktop (optional): For integration with Anthropic's Claude interface.

Installation

  1. Clone the Repository:

    git clone https://github.com/kukapay/chainlink-feeds-mcp.git
cd chainlink-feeds-mcp

  2. Install Dependencies:

    npm install

    The project requires:

    • @modelcontextprotocol/sdk: For MCP server functionality.

    • ethers: Version 6.x for blockchain interactions.

    • zod: For input validation.

    • dotenv: For environment variable management.

  3. Configure MCP Client: To use this server with an MCP client like Claude Desktop, add the following to your config file (or equivalent):

    {
  "mcpServers": {
    "chainlink-feeds-mcp": {
      "command": "node",
      "args": ["path/to/chainlink-feeds-mcp/index.js"],
      "env": { "INFURA_API_KEY": "your_api_key_here" }
    }
  }
}

Usage

The server exposes five tools via the MCP protocol, accessible through Claude Desktop (for natural language queries) or MCP Inspector (for JSON inputs). Below are the tools, with examples in both natural language (via Claude Desktop) and JSON formats.

Tool: getLatestPrice

  • Description: Fetches the latest price for a given pair on a specified chain, returns a JSON object like this:

    {
  "chain": "ethereum",
  "pair": "FIL/ETH",
  "price": 0.01234,
  "decimals": 18,
  "roundId": "123456",
  "timestamp": "2025-04-17T12:00:00.000Z",
  "proxyAddress": "0x0606Be69451B1C9861Ac6b3626b99093b713E801",
  "feedCategory": "medium"
}

  • Parameters:

    • pair (string): The price feed pair, e.g., FIL/ETH.

    • chain (string): The blockchain network, e.g., ethereum.

  • Natural Language Example (Claude Desktop):

    Input: "What¡¯s the latest FIL/ETH price on Ethereum?"

    Output: "The latest FIL/ETH price on Ethereum is 0.01234, with 18 decimals, round ID 123456, updated at 2025-04-17 12:00:00 UTC."

Tool: queryPriceByRound

  • Description: Queries the price for a given pair and round ID on a specified chain, returns a JSON object like this:

    {
  "chain": "ethereum",
  "pair": "FDUSD/USD",
  "price": 1.0001,
  "decimals": 8,
  "roundId": "123",
  "timestamp": "2025-04-17T12:00:00.000Z",
  "proxyAddress": "0xfAA9147190c2C2cc5B8387B4f49016bDB3380572",
  "feedCategory": "medium"
}

  • Parameters:

    • roundId (string): The round ID for the price data.

    • pair (string): The price feed pair, e.g., FDUSD/USD.

    • chain (string): The blockchain network, e.g., ethereum.

  • Natural Language Example (Claude Desktop):

    Input: "Can you get the FDUSD/USD price for round ID 123 on Ethereum?"

    Output: "For round ID 123, the FDUSD/USD price on Ethereum is 1.0001, with 8 decimals, updated at 2025-04-17 12:00:00 UTC. Note: This is a placeholder response due to historical data limitations."

Tool: listSupportedChains

  • Description: Returns a comma-separated list of all supported blockchain networks.

  • Parameters: None.

  • Natural Language Example (Claude Desktop):

    Input: "Which blockchain networks does this server support?"

    Output: "The server supports the following networks: ethereum, bsc, base, starknet, linea, mantle, scroll, zksync, celo."

Tool: listSupportedFeeds

  • Description: Returns a Markdown list of all supported chains and their price feed names.

  • Parameters: None.

  • Natural Language Example (Claude Desktop):

    Input: "Can you list all the price feeds supported by the server?"

    Output: "Here are the supported price feeds by chain:

    • Ethereum: FIL/ETH, FDUSD/USD, UNI/ETH, ...

    • BNB Chain: DOT/USD, CAKE/USD, BUSD/BNB, ...

    • Base: AXL/USD, USDC/USD, WIF/USD, ...

    • Starknet: ETH/USD, BTC/USD, WSTETH/ETH, ...

    • Linea: ETH/USD, FOXY/USD, MATIC/USD, ...

    • Mantle: MNT/USD, USDT/USD, BTC/USD, ...

    • Scroll: SCR/USD, STETH/USD, WBTC/BTC, ...

    • zkSync: ZK/USD, PEPE/USD, TRUMP/USD, ...

    • Celo: CELO/USD, CUSD/USD, NGN/USD, ..."

Tool: listSupportedFeedsByChain

  • Description: Returns a comma-separated list of price feed names for a specified blockchain network.

  • Parameters:

    • chain (string): The blockchain network, e.g., base.

  • Natural Language Example (Claude Desktop):

    Input: "What price feeds are available on the Base chain?"

    Output: "The Base chain supports the following price feeds: AXL/USD, USDC/USD, WIF/USD, CBETH/ETH, ..."

License

This project is licensed under the MIT License.

Available Tools

5 tools
getLatestPriceB

Fetches the latest price for a given pair on a specified chain

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool fetches data, implying a read-only operation, but doesn't cover aspects like error handling, rate limits, authentication needs, or response format. This leaves significant gaps in understanding how the tool behaves beyond its basic function.

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?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized and front-loaded, making it easy to parse quickly, with no wasted information.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description is incomplete for a tool that likely interacts with external data sources. It doesn't explain what 'latest price' entails (e.g., timestamp, source), error cases, or how results are structured, leaving the agent with insufficient context for reliable use.

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

Parameters4/5

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

The input schema has 0 parameters with 100% coverage, so no parameters need documentation. The description mentions 'a given pair on a specified chain', which hints at expected inputs but doesn't add detailed semantics since there are no parameters to describe. This meets the baseline for tools with zero parameters.

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

Purpose4/5

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

The description clearly states the action ('fetches') and target ('latest price for a given pair on a specified chain'), making the purpose understandable. It doesn't explicitly differentiate from siblings like 'queryPriceByRound', but it's specific enough to convey the tool's function without being vague or tautological.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives such as 'queryPriceByRound' or the list tools. It implies usage for fetching latest prices but lacks explicit context, exclusions, or prerequisites, leaving the agent to infer based on tool names alone.

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

listSupportedChainsB

Returns a comma-separated list of all supported blockchain networks

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the return format ('comma-separated list') but lacks details on error handling, rate limits, authentication needs, or whether the list is static or dynamic. This is a significant gap for a tool with zero annotation coverage.

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?

The description is a single, efficient sentence with zero waste. It's front-loaded with the core action and resource, making it easy to parse quickly.

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

Completeness3/5

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

Given the tool's simplicity (0 parameters, no output schema, no annotations), the description is adequate but has clear gaps. It explains what the tool does but lacks behavioral context and usage guidelines. For a read-only list tool, this is minimally viable but could be more helpful.

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

Parameters4/5

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

The tool has 0 parameters, and schema description coverage is 100% (though empty). The description doesn't need to add parameter details, so it meets the baseline for no parameters. It does mention the output format ('comma-separated list'), which adds slight value beyond the schema.

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

Purpose4/5

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

The description clearly states the verb ('Returns') and resource ('comma-separated list of all supported blockchain networks'), making the purpose unambiguous. However, it doesn't explicitly differentiate from sibling tools like 'listSupportedFeeds' or 'listSupportedFeedsByChain', which also list things but with different scopes.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, context for usage, or compare it to siblings like 'listSupportedFeeds' or 'listSupportedFeedsByChain', leaving the agent to infer usage based on tool names alone.

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

listSupportedFeedsA

Returns a Markdown list of all supported chains and their price feed names

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

A4/5.0
Behavior3/5

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

With no annotations provided, the description carries the full burden. It discloses the output format (Markdown list) and scope (all supported chains and feed names), which is useful behavioral context. However, it lacks details on potential limitations like rate limits, error handling, or data freshness.

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?

The description is a single, efficient sentence that front-loads the core action and output format with zero wasted words, making it easy to parse quickly.

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

Completeness4/5

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

Given the tool's simplicity (0 parameters, no annotations, no output schema), the description is complete enough for a read-only listing operation. It clearly states what is returned, though adding minor context like data source or update frequency could improve it further.

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

Parameters4/5

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

The tool has 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description appropriately focuses on output semantics, earning a baseline score of 4 for not introducing unnecessary complexity.

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?

The description clearly states the specific action ('Returns') and the resource ('a Markdown list of all supported chains and their price feed names'), distinguishing it from siblings like 'getLatestPrice' (which fetches specific prices) and 'listSupportedChains' (which likely lists only chains without feed details).

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

Usage Guidelines3/5

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

The description implies usage when needing a comprehensive list of chains and feeds, but does not explicitly state when to use this tool versus alternatives like 'listSupportedFeedsByChain' (which might filter by chain) or 'queryPriceByRound' (which queries specific data). No exclusions or prerequisites are mentioned.

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

listSupportedFeedsByChainB

Returns a comma-separated list of price feed names for a specified blockchain network

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool returns a comma-separated list, which is useful, but it doesn't cover other behavioral aspects such as error handling, rate limits, or authentication requirements. For a tool with zero annotation coverage, this is a significant gap in transparency.

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?

The description is a single, efficient sentence that front-loads the key information ('Returns a comma-separated list of price feed names') without any wasted words. It is appropriately sized for the tool's simplicity and zero parameters.

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

Completeness3/5

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

Given the tool has no parameters, no annotations, and no output schema, the description is minimally adequate. It explains what the tool does but lacks details on behavioral traits, usage context, or output format beyond 'comma-separated list'. For a tool in a set with siblings like 'listSupportedFeeds', more context on differentiation would improve completeness.

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

Parameters4/5

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

The tool has 0 parameters, and schema description coverage is 100%, so the schema already documents this fully. The description adds no parameter information, but with no parameters, the baseline is 4 as it doesn't need to compensate for any gaps. It implies a blockchain network is specified, but this is not reflected in the input schema, which might be a minor oversight.

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

Purpose4/5

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

The description clearly states the tool's purpose with a specific verb ('Returns') and resource ('comma-separated list of price feed names'), and it specifies the target ('for a specified blockchain network'). However, it doesn't explicitly differentiate from sibling tools like 'listSupportedFeeds' or 'listSupportedChains', which appears to be a related functionality.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'listSupportedFeeds' or 'listSupportedChains', nor does it specify prerequisites or exclusions for usage, leaving the agent to infer context from the tool name alone.

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

queryPriceByRoundC

Queries the price for a given pair and round ID on a specified chain (placeholder due to historical data limitations)

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations, the description carries the full burden but only vaguely hints at behavior ('placeholder due to historical data limitations'), without disclosing operational traits like error handling, data sources, or limitations. It fails to add meaningful context beyond the basic purpose.

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

Conciseness3/5

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

The description is brief but front-loaded with the core purpose. The second sentence ('placeholder due to historical data limitations') is somewhat redundant and doesn't add value, reducing efficiency. Overall, it's concise but could be more structured.

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

Completeness2/5

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

Given the lack of annotations and output schema, the description is incomplete for a query tool. It doesn't explain return values, error cases, or how it differs from siblings like 'getLatestPrice', leaving significant gaps in contextual understanding.

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

Parameters4/5

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

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description mentions parameters ('pair', 'round ID', 'chain') but doesn't add semantics beyond what's implied, which is acceptable given the baseline. However, the placeholder note adds minor confusion.

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

Purpose3/5

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

The description states the tool 'queries the price for a given pair and round ID on a specified chain', which provides a clear verb ('queries') and resource ('price'), but it's vague about the specific context (e.g., what type of price or system). The phrase 'placeholder due to historical data limitations' adds confusion rather than clarity, making the purpose less definitive.

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

Usage Guidelines2/5

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

No explicit guidance is provided on when to use this tool versus alternatives like 'getLatestPrice' or other sibling tools. The description implies it's for historical data queries but doesn't specify scenarios or prerequisites, leaving the agent without clear usage context.

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

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose with no ambiguity. getLatestPrice fetches current prices, listSupportedChains lists networks, listSupportedFeeds provides detailed feed information, listSupportedFeedsByChain filters feeds by chain, and queryPriceByRound handles historical queries. The descriptions clearly differentiate their scopes and use cases.

Naming Consistency4/5

The naming is mostly consistent with a clear verb_noun pattern (e.g., getLatestPrice, listSupportedChains), but there is a minor deviation with queryPriceByRound which uses 'query' instead of 'get' or 'list'. This slight inconsistency does not significantly hinder readability or predictability.

Tool Count5/5

With 5 tools, the count is well-scoped for a Chainlink price feeds server. Each tool earns its place by covering essential operations like fetching prices, listing supported chains and feeds, and querying historical data, without being overly sparse or bloated.

Completeness4/5

The tool set provides strong coverage for the domain of Chainlink price feeds, including current and historical price queries, and listing supported networks and feeds. A minor gap exists in the placeholder note for queryPriceByRound due to historical data limitations, but core workflows are well-covered without significant dead ends.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • bridge-rates-mcp

    kukapay
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that delivers real-time cross-chain bridge rates and optimal transfer routes to onchain AI agents.
    15
    5
    MIT

  • @y0exchange/mcp

    y0exchange
    A
    license
    Not graded
    quality
    D
    maintenance
    An MCP server that gives AI agents real-time access to DeFi across multiple chains, enabling non-custodial crypto trading, portfolio queries, and transaction execution.
    14
    7
    MIT

  • Chainlink MCP Server

    junct-bot
    F
    license
    Not graded
    quality
    D
    maintenance
    MCP server providing agent-ready access to Chainlink's API for DeFi and crypto tools.

Appeared in Searches

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/kukapay/chainlink-feeds-mcp'

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