Authenticated hosted Streamable HTTP MCP server for crypto data routing through PubFi capability and gateway tools.
Scored across 4 tools
Each tool targets a distinct operation: single capability lookup, catalog enumeration, route execution, and runtime upgrade verification. There is no meaningful overlap or risk of selecting the wrong tool for a given task.
All tools follow the same pubfi.<resource>.<action> dotted convention with consistent snake_case and clear verbs. The naming pattern is uniform and predictable across the entire server.
Four tools is compact but reasonable for a focused PubFi gateway client covering discovery, execution, and verification. The surface is slightly thin for a broadly named server, but each tool earns its place within the stated scope.
The set covers capability discovery via list/get, execution via route.execute, and a specialized runtime upgrade verification flow. Minor gaps exist, such as no separate route listing or upgrade submission tool, but the apparent core workflows are supported.
Return the full typed request, response, metering, and readiness contract for one exact capability id from the installed Registry generation.
| Name | Required | Description | Default |
|---|---|---|---|
| capability_id | Yes | Exact capability id returned by pubfi.capabilities.list. |
| Name | Required | Description |
|---|---|---|
| manifest | Yes | |
| capability | Yes | |
| generation | Yes | |
| compiled_at | Yes | |
| observed_at | Yes | |
| schema_version | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is fully covered by structured data. The description adds context about the source ('installed Registry generation') and the scope of what is returned (request, response, metering, readiness), which goes slightly beyond the annotations. However, it does not disclose failure behavior for an unknown or inactive capability id. There is no contradiction with 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?
One dense sentence with zero filler. Every phrase — 'full typed', 'one exact', 'installed Registry generation' — carries meaningful information, and the most important content (what is returned) is front-loaded. There is no redundancy with the schema or annotations.
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 single-parameter, idempotent, read-only lookup tool, the description adequately covers purpose, input source, and return shape. The only notable omission is the error behavior when the requested capability id is not present in the installed Registry generation, which is the most likely failure mode. Given the tool's simplicity, this is a minor gap rather than a serious deficiency.
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 is a single required parameter and the schema itself provides a descriptive definition ('Exact capability id returned by pubfi.capabilities.list'), giving 100% schema description coverage. The tool description adds modest framing by tying the id to a 'full typed contract', but it adds no format, depth, or syntax meaning beyond what the schema already documents. A baseline of 3 is appropriate given the high coverage.
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 specific verb with a concrete deliverable: 'Return the full typed request, response, metering, and readiness contract.' It scopes the operation to 'one exact capability id', which cleanly separates it from the lookup flow implied by pubfi.capabilities.list, and anchors the result to 'the installed Registry generation'. Every element — resource, scope, and source — is explicit and non-tautological.
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 tool's own description states the use case (fetching the full contract for a single known id), and the parameter schema reinforces the expected workflow by requiring an 'Exact capability id returned by pubfi.capabilities.list'. However, the description itself does not explicitly state when not to use this tool or name alternative tools for enumerating or invoking capabilities. This is clear context without a formal exclusion statement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Enumerate the complete installed Registry v2 catalog as deterministic compact pages. The server does not rank, infer intent, or choose a capability.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum compact capability summaries to return. | |
| cursor | No | Opaque generation-bound cursor returned by the preceding page. | |
| method | No | ||
| provider_key | No | Optional exact public provider key. This is a static filter, not semantic search. |
| Name | Required | Description |
|---|---|---|
| filters | Yes | |
| manifest | Yes | |
| generation | Yes | |
| compiled_at | Yes | |
| next_cursor | No | |
| observed_at | Yes | |
| capabilities | Yes | |
| schema_version | Yes | |
| total_capability_count | Yes | |
| matching_capability_count | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive behavior. The description adds valuable beyond-annotation context: deterministic compact pages and the guarantee that no ranking, intent inference, or capability selection occurs. This meaningfully shapes an agent's expectations about response ordering and filtering.
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 tightly scoped sentences. The first front-loads the primary function and resource, and the second clarifies a key behavioral guarantee without 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?
With a strong input schema, an output schema, and informative annotations, the description needs to cover only the non-obvious behavioral and pagination context, which it does well. The main minor gap is not explicitly routing the agent to pubfi.capabilities.get for single-capability retrieval or to pubfi.route.execute for intent-based selection.
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 strong descriptions for limit, cursor, and provider_key, covering 75% of parameters with useful constraints and defaults. The description adds supportive context about deterministic paging and static filtering, but it does not clarify the method parameter or explain parameter interplay beyond what the schema states.
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 specific verb—'Enumerate'—and names the exact resource: the complete installed Registry v2 catalog. It also clarifies the tool's non-semantic, non-selecting behavior, which distinguishes listing from the route-execution sibling.
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 clearly implies this tool is for deterministic, complete catalog enumeration and explicitly says the server does not rank, infer intent, or choose a capability. However, it does not name alternatives or state explicit when-to-use versus when-not-to-use conditions relative to the sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Execute one exact GET or POST path through the authenticated PubFi account lane and the same Registry v2 matcher and typed executor as the HTTP gateway. Append :free only when the capability catalog publishes that exact account-scoped free variant.
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | Exact optional ASCII request-body bytes. For JSON routes, supply one compact serialized JSON document rather than a nested MCP argument value. | |
| query | No | Exact ASCII raw query string without a leading question mark. | |
| method | Yes | ||
| raw_path | Yes | Exact original URI path consumed by the Registry matcher. Segments use canonical unreserved ASCII only; percent escapes, dot segments, query, fragment, and backslash are forbidden. | |
| request_id | No | ||
| idempotency_key | No |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate destructiveHint=true and idempotentHint=false, which the description does not contradict. The description mentions 'execute' and a conditional 'Append :free' behavior, adding some transparency beyond the annotations. However, it does not describe side effects, idempotency implications, or what happens on failure, leaving gaps in understanding the full behavioral impact.
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 but dense, using jargon and a single complex sentence. It is not broken into clear parts and lacks a structured presentation of the tool's behavior and nuances. While not verbose, it sacrifices clarity for brevity.
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 leaves out critical contextual details: it does not mention expected return values, error handling, or how the conditional free variant affects the request or response. Given the tool's apparent complexity (route execution, account scoping, conditional behavior), the description is insufficient for an agent to predict outcomes reliably beyond the basic execution.
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 provides descriptions for some parameters (body, query, raw_path), but the tool description does not explain any parameter semantics itself. It only mentions the overall execution behavior, not how the parameters like method, request_id, or idempotency_key are used. The schema coverage is partial, and the description adds no parameter-level detail, making it hard for an agent to construct a correct request.
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 executes a GET or POST path through an authenticated account lane, using the same matcher/executor as the HTTP gateway. This conveys the core purpose, though it relies on domain-specific jargon like 'PubFi account lane' and 'Registry v2 matcher.' It is distinguishable from the sibling read-only tools, which are for 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 provides only conditional guidance ('Append :free only when the capability catalog publishes that exact account-scoped free variant') but does not explain when to choose this tool over alternatives or when not to use it. There is no explicit when/when-not context, leaving the decision largely to the agent's interpretation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Verify one reviewed Substrate System.apply_authorized_upgrade extrinsic through the authenticated account lane. Supply the expected Blake2b-256 hash of the FRAME System AuthorizedUpgrade code payload, not the active :code hash at the apply block. The server streams and discards provider runtime code, persists only a compact proof, and returns independent comparison evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| network | Yes | ||
| request_id | No | ||
| extrinsic_hash | No | Canonical lowercase 0x-prefixed 32-byte hash. | |
| extrinsic_index | No | ||
| idempotency_key | No | ||
| expected_authorized_code_hash | Yes | Canonical lowercase 0x-prefixed 32-byte hash. |
| Name | Required | Description |
|---|---|---|
| ok | Yes | |
| route | Yes | |
| matches | Yes | |
| provider | Yes | |
| upstream | Yes | |
| meter_key | Yes | |
| generation | Yes | |
| extrinsic_hash | Yes | Canonical lowercase 0x-prefixed 32-byte hash. |
| reserved_units | Yes | |
| credits_charged | Yes | |
| extrinsic_index | Yes | |
| upstream_status | Yes | |
| execution_status | Yes | |
| extrinsic_success | Yes | |
| computed_code_hash | Yes | Canonical lowercase 0x-prefixed 32-byte hash. |
| runtime_code_bytes | Yes | |
| execution_authority | Yes | |
| upstream_latency_ms | Yes | |
| provider_response_bytes | Yes | |
| provider_response_sha256 | Yes | |
| expected_authorized_code_hash | Yes | Canonical lowercase 0x-prefixed 32-byte hash. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description goes beyond the annotations by revealing important side effects: the server streams and discards provider runtime code, persists only a compact proof, and returns independent comparison evidence. It also signals the authenticated account lane, which is useful context not present 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 three tight sentences, front-loads the core verification operation, and then adds the most important input caveat and server behavior. Every sentence contributes essential information without repeating clues already in the schema.
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 core action, the key hash semantics, authentication context, and server-side storage/return behavior. It is complete except for deeper context around parameter semantics and explicit when-to-use conditions, which prevents a perfect score.
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 only 33%, so the description needed to explain the parameters; it adds the critical distinction for expected_authorized_code_hash as the Blake2b-256 hash of the payload, not the active code hash. However, it does not explain the meaning of network, extrinsic_hash vs extrinsic_index selection, request_id, or idempotency_key, leaving those gaps to the agent.
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 operation and resource: it verifies one reviewed Substrate System.apply_authorized_upgrade extrinsic. This is more precise than the sibling tools, which are generic capability discovery and routing 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 implies when it should be used by saying 'reviewed extrinsic' and by demanding the expected authorized upgrade hash rather than the active code hash. It does not explicitly state when to prefer this tool over alternatives or list exclusions, so usage guidance remains implicit rather than fully specified.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.