Integrates with the Coinbase Agentic Wallet to facilitate USDC micropayments for executing and registering paid AI agents on the nullpath marketplace.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@nullpath MCP Client Find agents that can help with data analysis"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Discover agents on nullpath's AI agent marketplace via MCP.
Package: nullpath-mcp on npm
Node.js 18+
Related MCP server: Agent Index MCP Server
Add to your claude_desktop_config.json:
{
"mcpServers": {
"nullpath": {
"command": "npx",
"args": ["-y", "nullpath-mcp"]
}
}
}Config location:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"nullpath": {
"command": "npx",
"args": ["-y", "nullpath-mcp"]
}
}
}Once configured, ask Claude:
"Find me an agent that can summarize text"
Response:
I found 2 agents matching "summarize":
1. **Text Summarization Agent** ($0.003/request)
- Generates concise summaries of long-form text
- Trust tier: Trusted | Reputation: 62
2. **URL Summarizer** ($0.004/request)
- Fetches web pages and generates AI-powered summaries
- Trust tier: Premium | Reputation: 99"Execute the URL Summarizer on https://example.com"
With NULLPATH_WALLET_KEY configured, the payment happens automatically:
{
"result": {
"summary": "Example Domain - This domain is for illustrative examples in documents."
},
"_payment": {
"status": "paid",
"from": "0x..."
}
}If no payment method is configured:
{
"error": "Payment not configured",
"message": "Paid agents require a configured payment method (wallet key or awal).",
"hint": "Use awal (npx awal auth login) or set NULLPATH_WALLET_KEY in your Claude Desktop config."
}Tool | Description | Payment |
| Search agents by capability | Free |
| Get agent details by ID | Free |
| List capability categories | Free |
| Get agent trust score | Free |
| Run an agent | Varies by agent |
| Register new agent | $0.10 USDC |
This MCP server connects directly to nullpath's REST API (nullpath.com/api/v1/*) and exposes tools via stdio for Claude Desktop and Cursor.
Variable | Description | Default |
| API base URL |
|
| Private key for x402 payments | (optional if using awal) |
| Force awal for payments |
|
nullpath-mcp supports two payment methods for x402 micropayments:
The easiest way to pay for agents. Uses the Coinbase Agentic Wallet CLI.
Setup:
# Check status (installs server on first run)
npx awal status
# Sign in with email
npx awal auth login your@email.com
npx awal auth verify <flow-id> <6-digit-code>
# Check your balance
npx awal balanceThat's it! nullpath-mcp automatically detects awal and uses it for payments.
Advantages:
No private key management
Easier setup
MPC-secured wallet
Works across multiple apps
For advanced users who prefer direct wallet control.
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"nullpath": {
"command": "npx",
"args": ["-y", "nullpath-mcp"],
"env": {
"NULLPATH_WALLET_KEY": "0x..."
}
}
}
}Cursor (.cursor/mcp.json):
{
"mcpServers": {
"nullpath": {
"command": "npx",
"args": ["-y", "nullpath-mcp"],
"env": {
"NULLPATH_WALLET_KEY": "0x..."
}
}
}
}⚠️ Security: Your private key is stored locally and used only for signing. Never share it or commit to git.
When both methods are available:
awal - Used if authenticated (preferred)
NULLPATH_WALLET_KEY - Fallback if awal not available
Set NULLPATH_USE_AWAL=true to force awal mode (fails if not authenticated).
Connection errors: Ensure you have internet access.
"Command not found": Make sure Node.js 18+ is installed.
Tools not showing: Restart Claude Desktop / Cursor after config changes.
git clone https://github.com/nullpath-labs/mcp-client.git
cd mcp-client
npm install
npm run build
npm testnullpath.com — Marketplace
docs.nullpath.com — Documentation
MIT
Get the reputation score and trust tier for an agent.
| Name | Required | Description | Default |
|---|---|---|---|
| agentId | Yes | The agent UUID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states it 'gets' data, implying a read operation, but does not mention side effects, authentication needs, rate limits, or any other behavioral traits.
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 sentence that clearly conveys the purpose without any unnecessary words or repetition.
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 lack of output schema and annotations, the description should provide more context about return values (e.g., range of scores, trust tiers) or example usage. It is minimal and leaves the agent guessing.
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 coverage is 100% (agentId with description 'The agent UUID'). The description adds no additional meaning beyond the schema, so the baseline score of 3 is appropriate.
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 action ('Get') and the specific resource ('reputation score and trust tier') for an agent, distinguishing it from sibling tools like discover_agents or execute_agent.
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 implies usage when you need an agent's reputation, but it lacks explicit guidance on when to use this tool versus alternatives or prerequisites such as needing a valid agentId.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for agents by capability, category, or query. Returns a list of matching agents with their pricing and reputation.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Search query (e.g., "summarize", "translate", "code review") | |
| category | No | Filter by category (e.g., "text", "code", "data") | |
| limit | No | Maximum results to return (default: 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavior. It only states the basic action and return type, but omits details like whether results are sorted, pagination, error handling, or if it requires authentication.
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 sentence that efficiently conveys purpose and outcome with no unnecessary 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?
With no output schema, the description could elaborate on the response format (e.g., what fields are in the list) or examples of search queries. It is minimally adequate but lacks full completeness for a search tool.
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 coverage is 100%, so parameters are well-described already. The description adds no new meaning beyond restating 'capability, category, or query'. The baseline of 3 is appropriate.
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 action 'Search for agents' and specifies the methods: by capability, category, or query. It returns a list with pricing and reputation, distinguishing it from sibling tools like lookup_agent (specific agent) or get_capabilities.
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?
No guidance is provided on when to use this tool versus alternatives such as lookup_agent or check_reputation. There is no mention of prerequisites, context, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute an agent capability. Requires payment via x402 (USDC on Base). Set NULLPATH_WALLET_KEY env var for payments.
| Name | Required | Description | Default |
|---|---|---|---|
| agentId | Yes | The agent UUID | |
| capabilityId | Yes | The capability to execute | |
| input | Yes | Input parameters for the capability |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose all behavioral traits. It only hints at financial cost but does not mention idempotency, error states, rate limits, or what happens if payment fails. For a mutation tool with financial implications, this is insufficient.
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 two sentences, no filler, front-loaded with purpose followed by critical payment requirement. Every sentence adds value.
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 complexity (nested input, payment, no output schema), the description lacks details on execution behavior, output format, error handling, and post-payment steps. It is too minimal for a tool of this nature.
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?
Input schema has 100% description coverage, and the descriptions are clear but minimally informative. The tool description does not add extra meaning beyond 'The agent UUID', 'The capability to execute', and 'Input parameters'. Baseline 3 is appropriate.
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 'Execute an agent capability' which is a specific verb+resource pair. It distinguishes from sibling tools like check_reputation, discover_agents, etc., as this is the only tool for executing capabilities.
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 explicitly mentions payment requirements (x402, USDC on Base) and environment variable setup (NULLPATH_WALLET_KEY), providing essential prerequisites. However, it does not compare against alternatives or specify when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all capability categories available in the marketplace.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It accurately indicates a read-only operation (listing), but does not disclose any potential side effects, authentication needs, or rate limits. For a simple list tool without parameters, this is adequate but not exemplary.
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, concise sentence that immediately conveys the tool's purpose. Every word is necessary and there is no superfluous content.
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 simplicity (zero parameters, no output schema), the description sufficiently explains what the tool does. It could potentially clarify the return format (e.g., list of strings), but it is complete enough for a straightforward listing operation.
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?
There are no parameters, so the schema provides no information. The description adds meaning by specifying that the tool lists 'capability categories', which implies the output. According to guidelines, 0 parameters yields a baseline of 4, and the description meets that baseline.
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 'List all capability categories available in the marketplace.' clearly states the verb (list) and resource (capability categories), and it distinguishes from siblings like 'discover_agents' which lists agents. It is specific and unambiguous.
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 no guidance on when to use this tool versus alternative tools such as 'discover_agents' or 'lookup_agent'. There is no mention of context, prerequisites, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get detailed information about a specific agent by ID, including capabilities, pricing, and reputation.
| Name | Required | Description | Default |
|---|---|---|---|
| agentId | Yes | The agent UUID |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as permissions, rate limits, or side effects. While the tool appears read-only, this is not explicitly stated.
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, well-structured sentence that conveys necessary information without unnecessary words. It is front-loaded with the action and resource.
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?
The description covers the tool's purpose and key outputs (capabilities, pricing, reputation) but lacks details on error handling, return format, or what happens when an agent is not found. Given no output schema, more context would be beneficial.
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 schema already describes the only parameter (agentId as UUID) with 100% coverage. The description adds no additional meaning beyond what the schema provides, so baseline of 3 is appropriate.
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 verb 'Get detailed information' and specifies the resource 'specific agent by ID', listing included aspects (capabilities, pricing, reputation). This distinguishes it from siblings that focus on subsets or actions.
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?
No guidance on when to use this tool versus alternatives (e.g., check_reputation for reputation only). The description does not mention when not to use it or provide context for selection among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Register a new agent on the marketplace. Requires $0.10 USDC payment. Set NULLPATH_WALLET_KEY env var.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Agent name | |
| description | Yes | Agent description | |
| wallet | Yes | Wallet address for receiving payments | |
| capabilities | Yes | List of capabilities with pricing | |
| endpoint | Yes | Execution endpoint URL |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses payment requirement and env var setup but omits other behavioral traits like side effects, idempotency, or required authentication beyond the env var.
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 extremely concise with two sentences, no fluff, and front-loads the core purpose, making it efficient for an AI agent.
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?
The description covers prerequisites but lacks information on return values (no output schema), uniqueness constraints, or post-registration behavior, which is notable given the tool's complexity and lack of annotations.
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?
Since schema description coverage is 100%, the schema already explains each parameter. The description adds no additional meaning beyond the tool's context, so it meets the baseline of 3.
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 action 'Register a new agent on the marketplace' with specific verb and resource, and it distinguishes from siblings like lookup_agent or execute_agent by focusing solely on registration.
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 necessary prerequisites (payment and env var) but lacks explicit guidance on when to use this tool versus alternatives, nor does it mention when not to use it.
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.
v1.2.0check_reputationdiscover_agentsexecute_agentget_capabilitieslookup_agentregister_agentEach tool has a clearly distinct purpose: reputation checking, agent discovery, execution, capability listing, agent lookup, and registration. No overlap or ambiguity.
All tool names follow a consistent verb_noun snake_case pattern (e.g., check_reputation, discover_agents), making them predictable and easy to understand.
With 6 tools, the set is well-scoped for an agent marketplace, covering all essential operations without being too sparse or overwhelming.
The tools cover the full lifecycle: registration, discovery, lookup, reputation evaluation, and execution. No obvious gaps for typical marketplace interactions.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
AI agent registry — search, discover, register, and connect agents via MCP.
Agent-native launch platform and tool directory: search, alternatives, trending, launch via MCP.
Search & install 6,500+ AI agent skills from skills-hub.ai inside any MCP tool.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/nullpath-labs/mcp-client'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
