This server gives MCP-capable agents a read-only, mostly free interface to the curated gold-402 x402 directory plus a paid human-judgement layer, so they can find x402 services and safely vet an endpoint before spending money on it.
gold402_search — free-text search of the curated directory, filterable by shelf, with pagination and provenance stamps.
gold402_list_sections — list all 13 shelves with curated entry counts, useful for choosing valid search filters.
gold402_get_entry — fetch a single directory entry by name, including URL, description, shelf, first-listed date, and permanent listing page.
gold402_check_endpoint — live-probe any x402 endpoint (listed or not) with one unpaid request to verify it answers, returns a real 402 challenge, and exposes payment terms plus the origin's manifest.
gold402_verdict — paid ($0.001 USDC on Base): get the 24K Labs editorial verdict and aggregated rater grades for a resource; call once to receive payment terms, sign with your own wallet, then call again with the signature to settle. The server never holds or moves your money.
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., "@gold402-mcp Find the directory for x402 services that accept image generation"
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.
An MCP server over gold-402 — the curated x402 directory maintained by 24K Labs. Gives any MCP-capable agent (Claude, Cursor, or anything speaking MCP) four tools for finding x402 services and for checking an endpoint before it spends money against it.
Status: v0.1 — tested, packaged, not yet published. Runs over stdio.
Tool | What it does |
| Search the shelf by free text and/or shelf name. Paginated. Every answer states how many entries it actually searched. |
| All 13 shelves with their true curated counts, and how many of each are searchable here. |
| One entry by name — URL, description, shelf, date first listed, permanent listing page. |
| Live-probe any x402 endpoint, listed or not. One unpaid request: does it answer, is it a real 402, what are the payment terms, does the origin publish a manifest — plus whether it's on our shelf. |
| Paid, $2.00 USDC on Base. The 24K Labs editorial verdict for one resource plus aggregated independent rater grades. The judgement layer — a maintainer looked at it and put a name behind it. |
Four of the five tools are free and stay free — search, shelves, entry lookup, and the live probe. No key, no wallet, no account.
gold402_verdict is paid: $2.00 USDC on Base (the live endpoint states the exact price in its 402; the number here is as of 2026-09-02). It is the only one, and it buys
the thing the free probe explicitly does not give you — a human judgement. A valid
402 proves the door works; the verdict is a maintainer saying it was worth a
stranger's money.
This server never holds a wallet and never pays on your behalf. Call
gold402_verdict once with no payment_signature and it hands back the decoded
x402 terms — price, network, asset, payTo, timeout. Sign them with your own wallet
and call again with the signature. The money goes from you to 24K Labs; this
process is not in the path.
gold402_check_endpoint is the door check the maintainers run, made callable.
It works on endpoints that are not in the directory, which is the point: an
agent about to pay a stranger can ask first.
Related MCP server: Secant Agent Research
The shelf is admitted under two rules and the difference is load-bearing. A
service is listed only if a maintainer probed its endpoint and it answered an
x402 request correctly at the time of review. A library, framework, guide or
community resource has no payable endpoint, is never asked for a 402, and is
listed on public reachability alone — do not read one of those as evidence that
it speaks the protocol. Either way we re-probe periodically. It is not an
audit of the provider, a guarantee of uptime, or a promise that any call will
succeed. Which entries carry a dated receipt — and which are unproven — is
published at https://24klabs.ai/.well-known/touchstone. A valid
402 proves the door works — not that the service delivers. Every response carries
an as_of stamp and the upstream it came from.
Absence from the directory is not a verdict against a service. It's a curated list, not a census.
Works today, nothing to sign up for:
pip install git+https://github.com/Haustorium12/gold402-mcp.git
gold402-mcpOr with no install step at all:
uvx --from git+https://github.com/Haustorium12/gold402-mcp.git gold402-mcpFrom a clone:
python3 -m venv .venv && ./.venv/bin/pip install -e .
./.venv/bin/gold402-mcpNot on PyPI yet, so plain
pip install gold402-mcpwill not resolve. The git form above is the real install and is verified working.
Claude Desktop / Claude Code (claude_desktop_config.json or .mcp.json):
{
"mcpServers": {
"gold402": {
"command": "uvx",
"args": ["--from", "git+https://github.com/Haustorium12/gold402-mcp.git", "gold402-mcp"]
}
}
}Installed with pip? Use "command": "gold402-mcp" with no args.
Two upstreams, both public, no key, no auth, no scraping:
https://24klabs.ai/api/directory/search?q=<text>§ion=<id> — full-shelf
search, free and ungated. gold402_search and gold402_get_entry query this
directly, so a search runs over every curated entry, and each result carries the
date it was last knocked.
https://24klabs.ai/directory.json — a summary view: shelf structure, true
per-shelf counts, and the 25 most recently listed entries. Used for
gold402_list_sections and as the fallback if search is unreachable. Cached 15
minutes; a stale cached copy is served with its age disclosed rather than hidden.
Coverage, stated plainly. Every response reports the curated total and how
many entries the query actually ran over. If the search endpoint is down and this
server falls back to the summary, the answer says so in its coverage line and a
miss is reported as unknown, never as absent. gold402_check_endpoint works on
any endpoint whether or not it is listed.
Until 2026-09-02, search ran over the 25-entry summary only and reported that as the whole shelf — 4.9% coverage presented as 100%. Fixed by querying the search endpoint; the coverage line is now the shelf's own number.
./.venv/bin/python test_tools.py # tool-level, incl. error paths
./.venv/bin/python test_stdio.py # end-to-end over the real MCP protocolBoth pass as of 2026-08-20, including against the installed console script
(clean venv, pip install from the built wheel) — not just the source file.
Curated by 24K Labs · directory: https://github.com/Haustorium12/gold-402
Live-probe ANY x402 endpoint — listed or not — before paying it. Sends one unpaid request and reports: whether it answered, the HTTP status, whether it returned a real 402 payment challenge, and the payment terms found (scheme, network, price, payTo, asset). Also checks the /.well-known/x402 manifest on the same origin. This is the same liveness-and-protocol check the gold-402 maintainers run at the door. It does NOT spend money and does NOT verify delivery — a valid 402 proves the door works, not that the service is good.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses specific behavioral details beyond annotations: it sends one unpaid request, does not spend money, does not verify delivery, and checks the manifest. These details are not captured by readOnlyHint or openWorldHint, adding valuable context for the agent to manage expectations.
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 front-loaded with the core purpose, followed by specific outputs and limitations. It is concise (five sentences) and every sentence adds value—no filler, no redundancy, and the structure flows logically.
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 that an output schema exists (not shown but indicated), the description need not detail return formatting. It covers the essential output elements (status, 402 challenge, payment terms, manifest check) and clearly states constraints (does not spend money, does not verify delivery), making it complete for an agent to decide when and how to use it.
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?
Despite the schema having descriptions for url, method, and response_format, the coverage signal is 0% (likely top-level params lacks description). The tool description does not compensate by explaining how to use these parameters; it omits any mention of method or response_format, leaving the agent to rely solely on schema descriptions for parameter guidance.
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: to live-probe any x402 endpoint, sending an unpaid request and reporting liveness, HTTP status, payment challenge, and terms. It explicitly distinguishes from siblings (search, list_sections, get_entry, verdict) by focusing on endpoint probing rather than content retrieval, and clarifies it applies to any endpoint, listed or not.
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 on when to use it ('before paying it') and explicitly states what it does NOT do (spend money or verify delivery). It implies this is for pre-payment validation but does not explicitly name alternative tools for delivery verification or content exploration, which minor gap prevents a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch a single gold-402 entry by name (exact match preferred, falls back to partial). Returns the full record including URL, description, shelf, the date it was first listed, and the permanent listing page.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses the matching behavior (exact then partial) and lists return fields. Annotations already provide safety hints (read-only, idempotent), so the description adds meaningful behavioral detail without redundancy.
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 concise sentences, free of fluff, and clearly structured. It communicates purpose and output without unnecessary detail.
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 low complexity (single entry fetch) and presence of an output schema, the description sufficiently covers the return content by listing all key fields (URL, description, shelf, date first listed, permanent listing page). No gaps found.
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?
Both parameters have schema descriptions, and the tool description enriches the 'name' parameter by explaining the exact/partial matching semantics. The response_format parameter is adequately described in the schema, so no additional clarification is needed.
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 fetches a single gold-402 entry by name, with exact match preferred and fallback to partial. This precisely defines the action and distinguishes from search-oriented siblings.
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?
It explicitly indicates when to use: to retrieve a single entry by name. While it doesn't contrast with sibling tools like gold402_search, the scope is unambiguous enough for the agent to select appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the shelves (categories) of the gold-402 directory with an entry count for each. Use the returned section id as the 'section' filter in gold402_search.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only/idempotent/non-destructive behavior, and the description adds beyond that by saying the tool returns counts and section IDs and how those IDs feed into search. This is useful behavioral/return context without contradicting the annotations.
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?
Two short, purposeful sentences: the first names the action and result, the second gives the concrete integration hint. No filler, repetition, or wasted 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 simple list tool with safe annotations, a one-parameter schema, and an output schema, this description is complete: it explains what the tool lists, what it returns, and how to use the result in a sibling tool. No missing contextual element is apparent.
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 is silent on the response_format parameter, but the schema itself documents that parameter thoroughly with an enum, default, and usage note. The description adds no parameter-level meaning beyond the schema, so a 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 uses a concrete verb and resource ('List the shelves (categories) of the gold-402 directory') and adds a useful output detail ('entry count for each'), clearly distinguishing it from the sibling search/retrieval/endpoint tools.
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 tells the agent the primary downstream use ('Use the returned section id as the 'section' filter in gold402_search'), which gives clear context for when to call it. It does not explicitly say when not to use it versus alternatives, so it stops short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the gold-402 curated directory of x402 services, MCP servers, SDKs, facilitators and tools. Every entry was hand-probed by a maintainer and answered an x402 request correctly at the time of review. Filter by free text and/or shelf; supports pagination. Returns name, URL, description, shelf and the date first listed, with a provenance stamp.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds context about the hand-probed, curated nature of entries and specifies output fields including provenance stamp, going beyond the annotation hints to give users confidence in reliability and result contents.
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 concise, front-loaded with the primary action, and structured in three clear sentences covering purpose, curation, and features. It avoids unnecessary detail.
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 detailed schema and output schema, the description provides sufficient context for usage without redundant explanations. It covers what the tool returns and the quality of entries, making it complete.
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 provides detailed descriptions for each parameter (limit, query, offset, section, response_format). The tool description only paraphrases filtering and pagination, adding minimal extra meaning beyond what the schema covers.
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 identifies the tool's function as searching the curated x402 directory, specifying the types of entries it covers. It distinguishes itself from sibling tools like list_sections and get_entry by focusing on search.
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 for searching and mentions filtering/pagination, but does not explicitly state when to prefer this tool over alternatives like list_sections. It lacks direct comparative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
PAID ($0.001 USDC on Base) — the 24K Labs editorial verdict for one x402 resource, plus aggregated independent rater grades, as JSON. This is the human judgement layer: a maintainer looked at this service and put a name behind it. Distinct from gold402_check_endpoint, which is FREE and only reports whether the door answered. Call once with no payment_signature to receive the exact payment terms; call again with the signature to settle. This server never holds a wallet — you pay 24K Labs directly from yours.
| Name | Required | Description | Default |
|---|---|---|---|
| params | Yes |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds meaningful behavioral context beyond those: the $0.001 USDC payment, the two-call settlement flow, and the fact that the server never holds a wallet. No contradiction with annotations.
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 dense but efficient: it front-loads the paid nature, defines the output, distinguishes the tool from a sibling, and explains the two-call flow in four short sentences. Minor redundancy with schema text on payment_signature costs it a point.
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 output schema exists and the main behavioral complexity is the payment handshake, the description is largely sufficient. It explains what the verdict contains, how to pay, and what makes it different from the free check. It does not mention the markdown response_format option, but that is visible in the schema.
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 adds useful meaning about the payment_signature workflow and the resource scope, but the schema already documents resource and payment_signature semantics. The claim that output is 'as JSON' is potentially confusing because response_format defaults to markdown and allows json, and response_format is not discussed in the description.
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 names a specific, differentiated purpose: 'the 24K Labs editorial verdict for one x402 resource, plus aggregated independent rater grades.' It also explicitly contrasts with gold402_check_endpoint, making the tool's role clear among its siblings.
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?
It gives concrete usage guidance: call once without payment_signature to receive payment terms, then call again with the signature to settle. It explicitly distinguishes from the free gold402_check_endpoint, though it does not address when to choose this over gold402_search, list_sections, or get_entry.
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.
v0.1.0gold402_check_endpointgold402_get_entrygold402_list_sectionsgold402_searchgold402_verdictScored across 5 tools
Each tool targets a distinct operation: browsing shelves, searching entries, fetching one entry, live-probing an endpoint, and retrieving a paid verdict. The free technical probe and paid editorial verdict are explicitly differentiated, so there is no realistic confusion.
Most tools follow a consistent gold402_verb_noun pattern (gold402_list_sections, gold402_get_entry, gold402_check_endpoint, gold402_search). The one exception is gold402_verdict, which uses a noun instead of a verb, creating a minor but noticeable deviation.
Five tools is exactly right for this directory-style MCP server. Each tool earns its place: browse, search, detail, live verification, and paid human judgment. The scope is tight and no tool feels redundant.
The server covers the full user workflow: discover categories, search entries, retrieve full records, independently probe any endpoint, and optionally purchase an editorial verdict. The paid verdict flow with signature-based settlement is included, so there are no dead ends.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Meta-search MCP for x402 agent-payable services -- find paid APIs across every registry.
Search 15K+ MCP services, A2A agents, and x402 APIs from 5 registries. Paid via x402 (USDC on Base).
Discover machine-payable APIs, probe x402 payment terms, and run seller operations. Non-custodial.
Pay-per-action access to APIs and MCP tools over Lightning L402 and Base USDC x402.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Haustorium12/gold402-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server