Paid MCP web research for agents: search, extraction, citations, and x402 payment discovery.
Scored across 6 tools
search and research_pack overlap because research_pack bundles search plus extraction and citations, and extract_page also overlaps with research_pack. The remaining tools (monitor_diff, codex_audit, procure_request) are more distinct, but the boundaries between search, extract_page, and research_pack require careful reading.
All names use snake_case, but the patterns are mixed: extract_page, monitor_diff, and procure_request follow verb_noun, while codex_audit and research_pack are noun phrases and search is a single verb. It remains readable but lacks a predictable verb convention.
Six tools is well-scoped for a research-agent service, with each tool representing a plausible capability rather than redundant padding. The count is comfortably within the typical 3-15 range.
The surface covers core research operations: search, extraction, bundled research, diff monitoring, audit, and procurement. Minor gaps exist around codex_audit job lifecycle retrieval/status and clearer procurement/payment state handling, but agents can likely work around these.
Paid x402 Codex audit entrypoint. Use the REST /codex/jobs endpoint to queue execution.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Code, configuration, or architecture review prompt for the paid Codex audit. | |
| payment | Yes | x402 payment proof payload containing resource, amount, wallet, and settlement metadata. | |
| facilitator_id | No | Settlement facilitator id. Use evm-base for Base USDC payments. | evm-base |
| payment_identifier | No | Optional idempotency key. Reuse it on retries to return the cached paid result. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description is minimal. It does not disclose whether the tool is a read or write operation, side effects, authentication needs, or rate limits. The phrase 'paid' hints at payment but lacks specifics.
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 very short but under-specified. It sacrifices clarity for brevity, and the mention of a REST endpoint feels out of place.
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?
Despite having an output schema and full parameter coverage, the description lacks essential context about the tool's workflow, payment handling, and idempotency. It is incomplete for an agent to confidently invoke.
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 covers 100% of parameters with descriptions, so the description adds no extra semantic value. 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 identifies the tool as a 'paid x402 Codex audit entrypoint' but does not clearly state what action the tool performs. The reference to a REST endpoint is ambiguous and fails to differentiate this tool from 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?
No explicit guidance on when to use or avoid this tool. The description mentions using a REST endpoint but provides no context compared to alternatives like extract_page or search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid x402 page extraction for one to twenty URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| urls | Yes | HTTP URLs to extract. Limited to 20 pages per request. | |
| payment | Yes | x402 payment proof payload containing resource, amount, wallet, and settlement metadata. | |
| facilitator_id | No | Settlement facilitator id. Use evm-base for Base USDC payments. | evm-base |
| payment_identifier | No | Optional idempotency key. Reuse it on retries to return the cached paid result. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses that the operation is paid and limited to 20 URLs, but does not explain payment mechanics, failure modes, or authorization requirements. This is insufficient for a paid tool.
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 a single sentence. It front-loads key information (paid, x402, range). However, it could be slightly more informative without being verbose, e.g., mentioning the payment requirement leads to a score of 4 rather than 5.
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 of a paid extraction tool with an output schema and nested objects, the description is too sparse. It lacks details about the x402 protocol, payment flow, and appropriate use cases relative to sibling tools. The output schema exists but the description should still provide high-level context.
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 baseline is 3. The description adds no additional meaning beyond what the schema already provides (e.g., URL count is already in minItems/maxItems). No extra context on payment or facilitator_id semantics.
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 performs paid x402 page extraction for 1-20 URLs. It specifies the verb 'extraction' and resource 'page'. However, it does not explicitly differentiate from sibling tools like search or research_pack, though the 'paid' hint sets it apart.
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. There is no mention of prerequisites, exclusions, or typical scenarios. The description only states what it does, not when it should be used.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid x402 page diff monitor.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | HTTP URL to fetch and compare for the diff monitor. | |
| payment | Yes | x402 payment proof payload containing resource, amount, wallet, and settlement metadata. | |
| previous_hash | No | Optional previous content hash to compare against the current page. | |
| previous_text | No | Optional previous page text to compare against the current page. | |
| facilitator_id | No | Settlement facilitator id. Use evm-base for Base USDC payments. | evm-base |
| payment_identifier | No | Optional idempotency key. Reuse it on retries to return the cached paid result. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only mentions 'Paid x402' but does not disclose key behavioral traits such as required permissions, data handling, or side effects beyond the payment aspect.
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 very short, which is concise but lacks sufficient detail. It is front-loaded but at the cost of completeness.
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?
Despite having 6 parameters and an output schema, the description provides minimal context. It fails to explain core functionality, return behavior, or how the payment integrates with the diff monitoring.
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 covers 100% of parameters with descriptions. The tool description adds no additional meaning beyond the schema, so it meets the baseline expectation.
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 'Paid x402 page diff monitor' vaguely indicates it monitors page differences, but lacks a specific verb and clear resource object. It does not differentiate from siblings like extract_page or research_pack.
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 (codex_audit, extract_page, etc.). No context about prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Canonical durable procurement. Payment belongs in _meta[x402/payment], not task input.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | ||
| intent | No | ||
| offer_slug | Yes | ||
| max_budget_usd | Yes | ||
| max_latency_ms | No |
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 hints at durability (persistence) and reveals a non-obvious payment-channel convention, which is useful, but says nothing about side effects, spending behavior, auth requirements, latency limits, or failure/refund semantics for what is clearly a paid, mutating operation.
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 sentences with no filler, and the payment-placement rule is front-loaded. However, for a five-parameter paid tool this level of terse under-specification is a sizing problem rather than a virtue.
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 annotations, no output schema, a nested free-form input object, a required budget field, and zero schema descriptions, the description leaves the agent without the information needed to invoke this tool safely or correctly.
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?
All five parameters (offer_slug, input, max_budget_usd, max_latency_ms, intent) have 0% schema description coverage, and the description explains none of them. The nested free-form `input` object and the budget/latency constraints are entirely undocumented anywhere an agent can see.
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?
"Canonical durable procurement" is essentially a restatement of the tool name (procure_request) in jargon; it never states what is being procured, from whom, or what the tool actually returns. It distinguishes nothing from siblings like search or research_pack beyond the vague word "procurement."
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 only guidance is a field-placement rule (payment goes in _meta[x402/payment], not task input). There is no when-to-use, when-not-to-use, or alternative-tool guidance, which matters because this tool appears to spend money against max_budget_usd.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid x402 research pack: search plus extraction and citations.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query to run through the paid research API. | |
| payment | Yes | x402 payment proof payload containing resource, amount, wallet, and settlement metadata. | |
| max_results | No | Maximum number of ranked search results to return. | |
| extract_pages | No | Number of top search results to extract for the research pack. | |
| facilitator_id | No | Settlement facilitator id. Use evm-base for Base USDC payments. | evm-base |
| payment_identifier | No | Optional idempotency key. Reuse it on retries to return the cached paid result. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It mentions 'paid x402' but does not disclose how payment is processed, what happens on failure, or any other behavioral traits (e.g., idempotency via payment_identifier is only in the schema).
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 very concise (one sentence) but lacks structure or front-loading. It could be expanded to better serve the agent without being verbose.
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 presence of an output schema and 100% parameter coverage, the description still lacks completeness. It does not explain the payment process or when to use this tool over free alternatives, leaving gaps for an AI 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?
Schema description coverage is 100%, so baseline is 3. The description adds minimal value beyond the schema; it just says 'search plus extraction and citations' which is already implied by parameters.
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 it's a paid research pack that includes search, extraction, and citations. It distinguishes from siblings like 'search' (only search) and 'extract_page' (only extraction).
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 it is a paid tool but does not explicitly state when to use it versus alternatives (e.g., the free search tool). There is no guidance on when not to use it or mention of prerequisites like having a wallet for payment.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid x402 web search for autonomous agents.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search query to run through the paid research API. | |
| payment | Yes | x402 payment proof payload containing resource, amount, wallet, and settlement metadata. | |
| max_results | No | Maximum number of ranked search results to return. | |
| facilitator_id | No | Settlement facilitator id. Use evm-base for Base USDC payments. | evm-base |
| payment_identifier | No | Optional idempotency key. Reuse it on retries to return the cached paid result. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It reveals the payment requirement (x402) but omits other important traits such as caching behavior (only hinted by the idempotency key in schema), rate limits, or failure handling. The description is too brief to be transparent.
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 (one sentence) and front-loaded with the key paid aspect. However, it is under-specified for a tool with 5 parameters and an output schema; a slightly longer description with critical details would be more helpful.
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 complexity (5 params, payment payload, output schema) and lack of annotations, the description is insufficient. It does not cover the meaning of the output, how to construct the payment object, or practical usage context, leaving the agent with gaps.
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% with clear descriptions for all parameters, so the baseline is 3. The description adds no additional parameter context beyond what the schema provides, meaning it does not enhance understanding but also does not detract.
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 states it's a paid web search for autonomous agents, clearly indicating the tool's function and its paid nature. It distinguishes from siblings like research_pack and extract_page, which serve different purposes, but lacks detail on the specific resource or result type.
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. The description implies it's for paid searches but does not specify scenarios or exclusions, leaving the agent without decision rules.
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.
procure_requestcodex_auditextract_pagemonitor_diffresearch_packsearchx402 cited web research and synthesis for agents. $1.99 per completed brief.
Paid remote MCP for agent code search routing MCP, structured receipts, audit logs, and reviewer-rea
Live web search and research synthesis for agents, with free samples and x402 USDC payments.
Paid agent trust checks, receipt verification, research, data work, and monitoring.
Add one secure layer between your agents and this server.