Enables cross-chain token bridging, sending, and swapping between Solana and Base, supporting USDC, USDT, and SOL with automated quote retrieval, payment handling, and settlement tracking.
Send, swap, and bridge tokens cross-chain between Solana and Base — gasless, in one tool call. Built for AI agents using the Model Context Protocol (MCP).
Ask your AI agent any of these:
"Send 10 USDC from Solana to Base"
"How much would it cost to bridge 100 USDC to Base?"
"Transfer my SOL to Base as ETH"
"Swap 50 USDT from Base to Solana"
"Move my stablecoins cross-chain"
The server handles the entire flow: quote → payment → signing → submission → settlement.
Related MCP server: AgentServices
Add to your claude_desktop_config.json:
{
"mcpServers": {
"clawswap": {
"command": "npx",
"args": ["-y", "@clawswap/mcp-server"],
"env": {
"SOLANA_PRIVATE_KEY": "your-base58-solana-private-key",
"BASE_PRIVATE_KEY": "0x-your-hex-base-private-key"
}
}
}
}claude mcp add clawswap -- npx -y @clawswap/mcp-serverThen set environment variables:
export SOLANA_PRIVATE_KEY="your-base58-solana-private-key"
export BASE_PRIVATE_KEY="0x-your-hex-base-private-key"Add to .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):
{
"mcpServers": {
"clawswap": {
"command": "npx",
"args": ["-y", "@clawswap/mcp-server"],
"env": {
"SOLANA_PRIVATE_KEY": "your-base58-solana-private-key",
"BASE_PRIVATE_KEY": "0x-your-hex-base-private-key"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"clawswap": {
"command": "npx",
"args": ["-y", "@clawswap/mcp-server"],
"env": {
"SOLANA_PRIVATE_KEY": "your-base58-solana-private-key",
"BASE_PRIVATE_KEY": "0x-your-hex-base-private-key"
}
}
}
}codex mcp add clawswap -- npx -y @clawswap/mcp-serverOr add to ~/.codex/config.toml:
[mcp_servers.clawswap]
command = "npx"
args = ["-y", "@clawswap/mcp-server"]
env = { SOLANA_PRIVATE_KEY = "your-base58-solana-private-key", BASE_PRIVATE_KEY = "0x-your-hex-base-private-key" }Add to ~/.gemini/antigravity/mcp_config.json:
{
"mcpServers": {
"clawswap": {
"command": "npx",
"args": ["-y", "@clawswap/mcp-server"],
"env": {
"SOLANA_PRIVATE_KEY": "your-base58-solana-private-key",
"BASE_PRIVATE_KEY": "0x-your-hex-base-private-key"
}
}
}
}npx -y @smithery/cli install @clawswap/mcp-server --client claudeSupports multiple clients: claude, cursor, windsurf, cline, vscode, and more.
clawswap_bridgeBridge tokens between Solana and Base. Handles the entire flow automatically.
Parameter | Type | Required | Description |
| string | yes | Human-readable amount, e.g. "100", "0.5" |
| string | yes | Token symbol: USDC, USDT, SOL, ETH, WETH |
| "solana" | "base" | yes | Source chain |
| "solana" | "base" | yes | Destination chain |
| string | no | Destination address (defaults to agent's own) |
| string | no | Destination token (defaults to same or USDC) |
| number | no | Slippage tolerance 0-1 (default 0.01) |
clawswap_quotePreview a bridge quote without executing. Free, no payment required.
Same parameters as clawswap_bridge minus recipient.
clawswap_statusCheck the status of a previously initiated bridge.
Parameter | Type | Required | Description |
| string | yes | The requestId from |
Variable | Required | Description |
| For Solana→Base | Base58-encoded Solana private key |
| For Base→Solana | 0x-prefixed hex Base/EVM private key |
| No | Solana RPC (default: |
| No | Base RPC (default: |
You only need keys for the direction(s) you want to bridge. The server starts with whatever is configured.
Solana → Base: $0.50 USDC (paid automatically via x402 protocol, gas sponsored by ClawSwap)
Base → Solana: Free (agent pays ~$0.001 Base gas directly)
Solana: USDC, USDT, SOL
Base: USDC, USDT, ETH, WETH
MIT
Send, transfer, swap, or bridge tokens cross-chain between Solana and Base. Handles quoting, payment, signing, and submission automatically. Use this to move USDC, USDT, SOL, ETH, or WETH between chains.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Human-readable amount to bridge, e.g. '100', '0.5'. NOT base units. | |
| token | Yes | Token symbol on the source chain: USDC, USDT, SOL, ETH, WETH | |
| from | Yes | Source chain | |
| to | Yes | Destination chain | |
| recipient | Yes | Destination wallet address to receive the bridged tokens. | |
| destinationToken | No | Destination token symbol. Defaults to same token or USDC. | |
| slippage | No | Slippage tolerance 0-1. Default 0.01 (1%). |
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 usefully describes the tool's automated workflow (handles quoting, payment, signing, and submission) and lists supported tokens, which goes beyond basic functionality. However, it lacks critical behavioral details like whether this is a read-only or destructive operation, what permissions or authentication are needed, rate limits, or what happens on failure.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise and well-structured with two sentences. The first sentence clearly states the core functionality and automation, while the second provides specific usage context with supported tokens. Every word earns its place with zero redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a complex 7-parameter tool with no annotations and no output schema, the description is reasonably complete about what the tool does and its scope. However, it lacks important contextual information about the operation's nature (read vs. write), authentication requirements, error handling, and what the tool returns, which are significant gaps for a tool that presumably performs financial transactions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all 7 parameters thoroughly. The description adds marginal value by mentioning specific token symbols (USDC, USDT, SOL, ETH, WETH) which aligns with the schema, and implies the tool handles cross-chain operations, but doesn't provide additional parameter semantics beyond what's in the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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 specific verbs (send, transfer, swap, bridge) and resources (tokens between Solana and Base chains). It explicitly distinguishes this comprehensive tool from its sibling 'clawswap_quote' by mentioning it handles quoting, payment, signing, and submission automatically, while 'clawswap_quote' likely only provides quotes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool (to move specific tokens between Solana and Base chains) and implies an alternative by mentioning 'clawswap_quote' handles quoting, suggesting that tool might be for quote-only operations. However, it doesn't explicitly state when NOT to use this tool or fully differentiate from 'clawswap_status'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get a price quote for a cross-chain transfer between Solana and Base. Shows estimated output amount, fees, and time. Free, no payment required. Use before bridging to preview costs.
| Name | Required | Description | Default |
|---|---|---|---|
| amount | Yes | Human-readable amount, e.g. '100', '0.5' | |
| token | Yes | Token symbol on the source chain | |
| from | Yes | Source chain | |
| to | Yes | Destination chain | |
| destinationToken | No | Destination token symbol. Defaults to same token or USDC. | |
| slippage | No | Slippage tolerance 0-1. Default 0.01 (1%). |
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 does well by stating the tool is 'Free, no payment required' and that it 'Shows estimated output amount, fees, and time', which are important behavioral traits. However, it doesn't mention rate limits, authentication requirements, or error conditions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is perfectly concise with three sentences that each earn their place: states the purpose, lists what it shows, and provides usage guidance. It's front-loaded with the core functionality and wastes no words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a quote tool with no annotations and no output schema, the description does well by explaining what information will be returned ('estimated output amount, fees, and time') and the free nature of the call. However, without an output schema, it could benefit from more detail about the return format.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description doesn't add any parameter-specific information beyond what's already in the schema, which has 100% description coverage. The baseline score of 3 is appropriate since the schema already provides comprehensive parameter documentation.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
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 specific verbs ('Get a price quote') and resources ('cross-chain transfer between Solana and Base'), and distinguishes it from sibling tools by mentioning 'Use before bridging to preview costs' which implies clawswap_bridge is the actual execution tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit usage guidance with 'Use before bridging to preview costs', clearly indicating when to use this tool versus the clawswap_bridge sibling tool. It also mentions it's 'Free, no payment required' which helps set expectations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check the status of a previously initiated bridge using the requestId from clawswap_bridge.
| Name | Required | Description | Default |
|---|---|---|---|
| requestId | Yes | The requestId returned by clawswap_bridge |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that this is a read operation (checking status) and requires a 'requestId' from 'clawswap_bridge', which adds useful context. However, it doesn't describe behavioral traits like error handling, rate limits, or what the status response might include (e.g., pending, completed, failed).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the key information: the tool's purpose and parameter context. There is no wasted text, and every word earns its place by clarifying usage and dependencies.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (1 parameter, no output schema, no annotations), the description is adequate but has gaps. It explains the purpose and parameter semantics well, but lacks details on behavioral aspects like error cases or response format. For a status-checking tool, this leaves some uncertainty for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, so the baseline is 3. The description adds value by explaining that 'requestId' comes from 'clawswap_bridge', providing semantic context beyond the schema's technical description. This helps the agent understand the parameter's origin and purpose, elevating the score.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Check the status of a previously initiated bridge' with the specific resource being 'a previously initiated bridge' and the verb 'Check the status'. It distinguishes from its sibling 'clawswap_bridge' by specifying it's for checking status rather than initiating. However, it doesn't explicitly differentiate from 'clawswap_quote', which might be for getting quotes rather than checking status.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides clear context for when to use this tool: after initiating a bridge with 'clawswap_bridge' and needing to check its status using the 'requestId'. It implies an alternative by referencing 'clawswap_bridge' for initiation, but doesn't explicitly state when not to use it or compare with 'clawswap_quote'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.2clawswap_bridgeclawswap_quoteclawswap_statusEach tool has a clearly distinct purpose: clawswap_bridge executes transfers, clawswap_quote provides price estimates, and clawswap_status tracks transaction progress. There is no overlap or ambiguity in functionality, making tool selection straightforward for an agent.
All tools follow a consistent 'clawswap_' prefix with descriptive suffixes (bridge, quote, status), creating a predictable and readable pattern. This uniformity enhances clarity and usability across the tool set.
With 3 tools, the server is well-scoped for cross-chain bridging between Solana and Base. Each tool serves a distinct, essential function (execute, quote, status check), and there are no extraneous or missing tools for this focused domain.
The tool set provides complete coverage for the cross-chain bridging workflow: quoting (clawswap_quote), executing (clawswap_bridge), and monitoring (clawswap_status). This covers the full lifecycle from preview to completion without any obvious gaps or dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Multi-aggregator swap router for AI agents on Base. 10 bps fee. MCP-native, non-custodial.
Production-grade MCP gateway delivering 8 real-time AI tools with instant x402 micropayments settled in USDC on Base Mainnet or SPL-USDC on Solana. Features Basescan contract auditing, wallet analytics, headless browser scraping, and pre-scraped oracle data feeds.
Production-grade MCP gateway delivering 8 real-time AI tools with instant x402 micropayments settled in USDC on Base Mainnet or SPL-USDC on Solana. Features Basescan contract auditing, wallet analytics, headless browser scraping, and pre-scraped oracle data feeds.
Agent-commerce MCP server for x402/USDC payments and affiliate splits on Base.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/WarTech9/clawswap-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
