Skip to main content
Glama
deenesjakoruzh
heecheon92

SpecBridge MCP

by heecheon92
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

SpecBridge MCP

Translations: 한국어

SpecBridge MCP is a clone-and-own MCP starter for exposing API contract intelligence to AI agents. It works with OpenAPI documents directly and with Huma services through the OpenAPI documents Huma emits, turning those contracts into deterministic endpoint metadata, schemas, validation facts, referenced DTOs, and TypeScript declarations that agents can use before changing frontend or client code.

This project is intentionally repository-first rather than npm-published: clone it, adapt the backend registry to your private or public specs, and register the local MCP server with your agent host. The implementation keeps the core unopinionated by avoiding downstream file mutation, using a neutral public demo backend, supporting multiple injected backends, and treating inferred helpers as best-effort rather than guarantees.

Status: experimental. The tool surface is useful for local automation, but the repository is meant to be owned and adapted by each team.

Brief history

SpecBridge MCP started as a personal internal tool at SesameLab to improve the development cycle around backend API contracts, including Huma-backed services. In practice, giving AI agents structured contract data through MCP reduced hallucinations compared with asking them to read API documentation pages directly.

Related MCP server: MCP OpenAPI Server

Huma support status

Huma is supported through the OpenAPI-compatible documents that Huma services expose. That path has been smoke-tested with Huma-generated specs, JSON/YAML loading, and Unicode descriptions, but it is not yet a broad Huma conformance suite across many real services. Treat Huma support as intentionally supported and actively maturing rather than exhaustively proven.

What it provides

  • Configurable backend registry for one or many API contract specs

  • Huma-compatible support through Huma-generated OpenAPI JSON/YAML documents

  • Zero-config demo backend using a real public Swagger/OpenAPI URL

  • Spec loading and refresh with JSON/YAML support

  • Endpoint listing and filtering

  • Endpoint contract bundles with deterministic facts:

    • operation metadata

    • parameters

    • request and response schemas

    • referenced component schemas

    • endpoint-scoped TypeScript DTO declarations

    • validation facts such as required, nullable, enum, format, arrays, maps, and composition

  • TypeScript DTO declaration generation from component schemas

  • Best-effort proposal helpers that are explicitly secondary to deterministic spec facts

Project structure

.
├── README.md                         # User-facing setup, configuration, tool, and extension docs
├── README.ko-KR.md                   # Korean translation of README.md
├── AGENTS.md                         # Agent-facing project guide for future coding agents
├── package.json                      # pnpm scripts, runtime dependencies, and package metadata
├── tsconfig.json                     # Strict TypeScript build config; emits compiled JS into build/
├── biome.json                        # Biome formatter/linter config; excludes local-only backend config
├── mcp-server.sh                     # Thin shell wrapper that builds when needed and starts the MCP server
├── openapi.backends.example.json     # Committed working demo backend registry to copy for local use
├── openapi.backends.json             # Ignored local backend registry; create from the example when needed
├── src/
│   ├── index.ts                      # CLI entrypoint plus stdio/stateful HTTP/stateless HTTP transports
│   ├── mcp/register-tools.ts         # MCP tool registration and tool-level orchestration
│   └── openapi/
│       ├── config.ts                 # Backend registry loading, env precedence, defaults, and cache settings
│       ├── spec.ts                   # Spec fetching, parsing, endpoint lookup, schema facts, and DTO emission
│       └── types.ts                  # Shared OpenAPI/Huma-compatible contract types
├── tests/
│   ├── schema-dto.test.mjs           # Unit coverage for registry behavior, parsing, DTOs, and contract facts
│   ├── privacy.test.mjs              # Guardrail to keep publishable files free of internal/private tokens
│   └── e2e/mcp-stdio.test.mjs        # MCP stdio smoke test for representative tool calls
└── build/                            # Generated output from pnpm build; do not edit directly

The src/openapi directory name refers to the contract wire format. Huma support flows through the OpenAPI-compatible JSON/YAML documents generated by Huma services.

Non-goals

  • Publishing this project to npm for v1

  • Providing a generic installable CLI abstraction

  • Mutating downstream frontend/client repositories

  • Becoming a framework-specific client or SDK generator

  • Hosting specs or storing team API data remotely

Requirements

  • Node.js 18+

  • pnpm 10+

Install

git clone <your-fork-or-copy-url> specbridge-mcp
cd specbridge-mcp
pnpm install
pnpm build

Configure backends

SpecBridge includes a built-in public demo backend, so the tools work even when no local backend registry exists. Huma services are supported by pointing specUrl at the OpenAPI JSON/YAML document exposed by Huma, such as /openapi.json, /openapi.yaml, or your service-specific docs route.

Local backend definitions live in openapi.backends.json. This file is intentionally ignored by Git because it may contain private, local, or environment-specific API URLs.

The committed openapi.backends.example.json file contains a working Swagger Petstore demo backend. To create your local backend registry after cloning the repository:

cp openapi.backends.example.json openapi.backends.json

You can keep the copied demo backend to verify the MCP tools, replace it with an empty array ([]), or add your own backend definitions as needed:

[
  {
    "id": "local-service",
    "name": "Local Huma Service",
    "specUrl": "http://localhost:8080/openapi.json",
    "fallbackSpecUrls": ["http://localhost:8080/openapi.yaml"],
    "description": "Your local Huma/OpenAPI contract",
    "domainHints": ["/users", "/orders"]
  }
]

Alternatively, point OPENAPI_BACKENDS_FILE at another JSON file or set OPENAPI_BACKENDS directly.

Naming note: Huma vs OpenAPI

Huma emits OpenAPI-compatible contract documents, so some repository internals, tool names, and environment variables still use openapi in their names. Treat those names as references to the contract wire format, not as a limitation to non-Huma APIs. The MCP tools are intended for both plain OpenAPI specs and Huma-generated specs, with the Huma path still described as maturing until it has broader fixture coverage.

Configuration precedence

For a tool call, an explicit specUrl override is tried first for that call.

Backend registry sources are merged in this order, with later sources overriding earlier ones by id:

  1. Built-in public demo backend

  2. Repository-local openapi.backends.json, when present

  3. OPENAPI_BACKENDS_FILE, when set

  4. OPENAPI_BACKENDS, when set

DEFAULT_BACKEND_ID selects the default backend. If unset, SpecBridge uses swagger-petstore.

Environment variables

  • MCP_TRANSPORT: stdio or http

  • MCP_HTTP_HOST: HTTP bind host

  • MCP_HTTP_PORT: HTTP port

  • MCP_HTTP_PATH: MCP endpoint path, such as /mcp

  • MCP_HTTP_STATELESS: set to true for stateless HTTP mode

  • DEFAULT_BACKEND_ID: default backend ID

  • OPENAPI_BACKENDS: JSON array of backend configs

  • OPENAPI_BACKENDS_FILE: path to a backend config JSON file

  • OPENAPI_FETCH_TIMEOUT_MS: fetch timeout for spec loading

  • OPENAPI_CACHE_TTL_MS: in-memory spec cache TTL

  • OPENAPI_ENABLE_SWAGGER_UI_SCRIPT_EXTRACTION: opt in to strict JSON object extraction from static Swagger UI scripts; fetched JavaScript is never executed

Run

stdio mode

pnpm mcp
# or
./mcp-server.sh

HTTP mode

pnpm mcp:http

Stateless HTTP mode:

pnpm mcp:http:stateless

MCP host setup

Command-based stdio configuration

{
  "mcpServers": {
    "specbridge-mcp": {
      "command": "/absolute/path/to/specbridge-mcp/mcp-server.sh"
    }
  }
}

Codex config.toml example

[mcp_servers.specbridge-mcp]
args = ["/absolute/path/to/specbridge-mcp/mcp-server.sh"]
command = "bash"

HTTP URL

Start the server:

./mcp-server.sh --transport http --host 127.0.0.1 --port 3000 --path /mcp

Then connect your host to:

  • http://127.0.0.1:3000/mcp

If your host has trouble with session state, retry with --stateless.

Example prompts for AI agents

After this MCP server is connected to an agent host, human users can ask their AI agents contract-aware questions or implementation requests in natural language. The agent should use SpecBridge MCP tools as the source of contract data instead of guessing from memory or scraping documentation pages directly.

Examples:

  • "What backend services are available, and which backendId should I use for the school API?"

  • "List the endpoints related to student attendance, then show the request and response contract for the endpoint I should call."

  • "Using SpecBridge MCP, add the missing API model types and endpoint wrappers for the new student attendance endpoints in this codebase."

  • "Check whether the API contract has changed since this client code was written. If it has, update the affected DTOs, endpoint functions, and tests."

For implementation requests like these, SpecBridge provides the contract facts; the AI agent still decides how to modify the current codebase and should verify the resulting code with that project's tests.

Useful agent instructions:

  • "Use SpecBridge MCP only for API contract facts."

  • "Call list_backends first, then use the returned backendId for later calls."

  • "Do not directly visit private spec URLs; read contract data through the MCP tools."

  • "Treat propose_new_endpoint output as a proposal, not as source-of-truth contract data."

Tools

Recommended flow:

  1. list_backends

  2. load_openapi_spec

  3. list_api_endpoints

  4. get_endpoint_contract

  5. generate_typescript_dto

list_backends

Lists configured backend targets, the default backend ID, and optional domain hints.

load_openapi_spec

Loads or refreshes an OpenAPI-compatible contract document for a backend, including Huma-generated OpenAPI specs. Supports direct specUrl overrides.

list_api_endpoints

Lists endpoints from a loaded spec with optional tag, method, path substring, and limit filters.

get_endpoint_contract

Returns a deterministic endpoint contract bundle: operation metadata, parameters, request body, responses, referenced schemas, endpoint-scoped TypeScript DTO declarations, validation facts, and best-effort hints.

generate_typescript_dto

Generates TypeScript DTO declarations from a component schema name and includes referenced nested DTO types.

propose_new_endpoint

Returns a best-effort endpoint and DTO proposal aligned with patterns found in the current contract spec. Treat this as an agent aid, not a deterministic guarantee.

Extending with additional service layers

SpecBridge is intentionally small, so the safest extension pattern is to add one focused layer at a time and keep MCP tools thin.

Add another backend service from configuration only

If the service already exposes an OpenAPI or Huma-generated OpenAPI document, no code changes are required. Add it to your ignored local openapi.backends.json, or provide it through OPENAPI_BACKENDS_FILE/OPENAPI_BACKENDS:

[
  {
    "id": "billing-service",
    "name": "Billing Service",
    "specUrl": "https://billing.example.com/openapi.json",
    "fallbackSpecUrls": ["https://billing.example.com/openapi.yaml"],
    "description": "Billing API contract",
    "domainHints": ["/invoices", "/payments"]
  }
]

Use stable, lowercase id values because agents pass backendId back into every tool call. Add domainHints when multiple services may contain similarly named resources; they power endpoint-not-found suggestions.

Add code for a new service layer

Use this path when a service needs custom discovery, auth, post-processing, or tools that are not generic OpenAPI/Huma contract operations.

  1. Keep transport concerns in src/index.ts; do not add service-specific behavior there.

  2. Put shared service types in a focused types.ts file near that service layer.

  3. Put configuration and environment parsing in a focused config.ts file. Keep precedence explicit and test it.

  4. Put deterministic contract or service logic in a pure module. Avoid mutating downstream repositories from this MCP server.

  5. Register MCP-facing operations in src/mcp/register-tools.ts, or split registration into a service-specific register-*.ts module if the file becomes too large.

  6. Return both content and structuredContent from tools so agents can read human-friendly text and machine-friendly JSON.

  7. Add tests before relying on the layer: unit tests for parsing/edge cases, and an MCP smoke test when a new tool is exposed.

Good extension boundaries look like this:

src/
├── mcp/
│   ├── register-tools.ts             # calls registerOpenApiTools + any new registerXTools helpers
│   └── register-billing-tools.ts     # optional if a new service exposes distinct MCP tools
└── billing/
    ├── config.ts                     # billing-specific env/config loading
    ├── contract.ts                   # deterministic billing contract helpers
    └── types.ts                      # billing-specific DTO/helper types

Prefer deterministic facts over inference. When adding best-effort helpers, label them clearly in the output, keep them secondary to spec-derived facts, and include tests that lock the distinction.

Development

pnpm install
pnpm check
pnpm build
pnpm test

Useful scripts:

  • pnpm check: Biome check

  • pnpm format: apply Biome formatting

  • pnpm lint: Biome lint only

  • pnpm build: clean TypeScript build

  • pnpm test: build and run all tests

  • pnpm test:e2e: build and run MCP smoke tests

Clone-and-own guidance

SpecBridge is intentionally repository-first. Keep the core small, adapt backend configuration locally, and let downstream agents decide how to edit your client code. If your team needs custom auth, internal naming rules, or additional contract facts, add them in your clone rather than fighting a global package abstraction.

Available Tools

6 tools
generate_typescript_dtoB

Generate TypeScript DTO type declarations from OpenAPI components schema. Includes referenced nested DTO types.

ParametersJSON Schema
NameRequiredDescriptionDefault
backendIdYesRequired backend id from list_backends.
schemaNameYesComponent schema name under #/components/schemas.
specUrlNoOptional docs URL override for this call.

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions generating DTOs and including nested types, but fails to describe critical behaviors such as error handling, output format, or any constraints like rate limits or authentication needs. This leaves significant gaps in understanding how the tool operates beyond its basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence that efficiently conveys the tool's purpose and key feature (including nested DTOs). It is front-loaded with the main action and avoids unnecessary details, making it easy to understand quickly without wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (generating code from OpenAPI schemas) and the lack of annotations and output schema, the description is insufficient. It does not explain what the output looks like, how errors are handled, or any dependencies on other tools like 'list_backends'. This leaves the agent with incomplete information for effective tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 parameters thoroughly. The description does not add any meaning beyond what the schema provides, such as explaining relationships between parameters or usage nuances. With high schema coverage, the baseline score of 3 is appropriate as the description does not compensate but also does not detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Generate TypeScript DTO type declarations') and the source ('from OpenAPI components schema'), with additional detail about including referenced nested DTO types. It distinguishes itself from sibling tools like 'list_backends' or 'load_openapi_spec' by focusing on code generation rather than listing or loading operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when TypeScript DTOs are needed from OpenAPI schemas, but it does not explicitly state when to use this tool versus alternatives like 'get_endpoint_contract' or 'propose_new_endpoint'. No guidance is provided on prerequisites or exclusions, leaving usage context inferred rather than clearly defined.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_endpoint_contractA

Return full contract for one endpoint: params, request schema, response schema, and referenced DTO names.

ParametersJSON Schema
NameRequiredDescriptionDefault
backendIdYesRequired backend id from list_backends.
pathYesExact endpoint path from OpenAPI, e.g. /users/{id}.
methodYesHTTP method.
specUrlNoOptional docs URL override for this call.

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but only states what information is returned, not behavioral traits like whether this is a read-only operation, performance characteristics, error conditions, or authentication requirements. It doesn't disclose if this makes network calls, has rate limits, or what happens with invalid inputs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence efficiently conveys the tool's purpose with zero waste. Every word earns its place by specifying exactly what's returned. The structure is front-loaded with the main action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 parameters, 100% schema coverage, and no output schema, the description is minimally adequate but lacks context about the return format (structure of the contract), error handling, or how it relates to sibling tools. It states what information is returned but not in what format or with what limitations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 4 parameters thoroughly. The description doesn't add any parameter-specific meaning beyond what's in the schema descriptions (backendId from list_backends, exact path format, HTTP method enum, optional specUrl). Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Return full contract') and resource ('for one endpoint'), listing the exact components returned (params, request schema, response schema, DTO names). It distinguishes from siblings like list_api_endpoints (which lists endpoints) or load_openapi_spec (which loads full specs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when detailed endpoint information is needed, but doesn't explicitly state when to use this tool versus alternatives like load_openapi_spec or propose_new_endpoint. No exclusions or prerequisites are mentioned, though the required parameters suggest it's for retrieving specific endpoint details.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_api_endpointsC

List endpoints from the currently loaded OpenAPI document.

ParametersJSON Schema
NameRequiredDescriptionDefault
backendIdYesRequired backend id from list_backends.
tagNoFilter by tag name.
methodNoFilter by HTTP method (get/post/put/patch/delete/head/options).
pathContainsNoSubstring filter on path.
limitNoMax rows to return.
specUrlNoOptional docs URL override for this call.

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a listing operation but doesn't describe what the output looks like (e.g., format, pagination), whether it's read-only, or any rate limits or authentication requirements. The description is minimal and lacks essential behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's appropriately sized for a straightforward listing tool and front-loads the core purpose without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, no annotations, no output schema), the description is incomplete. It doesn't explain the output format, prerequisites (e.g., needing a loaded spec), or how filtering parameters interact. For a tool with multiple filtering options and no structured output documentation, more context is needed.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 6 parameters thoroughly. The description adds no parameter-specific information beyond implying filtering capabilities through 'from the currently loaded OpenAPI document.' This meets the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List endpoints') and resource ('from the currently loaded OpenAPI document'), providing a specific verb+resource combination. However, it doesn't differentiate from sibling tools like 'get_endpoint_contract' or 'propose_new_endpoint', which might have overlapping domains.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 alternatives. It doesn't mention prerequisites (like needing to load an OpenAPI spec first), nor does it contrast with siblings like 'get_endpoint_contract' for detailed endpoint information or 'list_backends' for backend management.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

list_backendsB

List configured backend targets available for OpenAPI tools.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

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 states the action ('List') but doesn't disclose behavioral traits like whether it's read-only, requires authentication, has rate limits, or what the output format might be. This leaves significant gaps for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the key information ('List configured backend targets') without any wasted words. It's appropriately sized for a simple tool with no parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., list format, data structure) or behavioral aspects, which is insufficient for a tool that might be used in a workflow with siblings like 'generate_typescript_dto'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0 parameters with 100% coverage, so no parameter documentation is needed. The description adds context by specifying 'configured backend targets available for OpenAPI tools,' which provides meaning beyond the empty schema, earning a baseline score above 3 for compensating with useful context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('List') and resource ('configured backend targets'), making the purpose evident. However, it doesn't explicitly differentiate from sibling tools like 'list_api_endpoints' or 'load_openapi_spec', which might also list related resources, so it lacks sibling differentiation for a perfect score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

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 alternatives. It doesn't mention context, prerequisites, or exclusions, such as whether it should be used before selecting a backend for other operations or how it relates to siblings like 'list_api_endpoints'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

load_openapi_specA

Load or refresh OpenAPI spec from a URL. Use this first if tools fail because docs path changed.

ParametersJSON Schema
NameRequiredDescriptionDefault
backendIdYesRequired backend id from list_backends.
urlNoOptional docs URL override for this call.
forceRefreshNoBypass in-memory cache when true.

TDQS

A4.1/5.0
Behavior3/5

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 mentions caching behavior ('Bypass in-memory cache when true' is implied through the forceRefresh parameter context) and the tool's role in system recovery, but lacks details on permissions, rate limits, error handling, or what 'load or refresh' actually entails operationally.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is perfectly concise with two sentences that each earn their place: the first states the core functionality, the second provides crucial usage guidance. It's front-loaded with the essential action and wastes no words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description provides adequate context for a tool with 3 parameters and 100% schema coverage. It explains the tool's purpose and when to use it, but doesn't address what happens after loading (e.g., how other tools are affected) or potential side effects, which would be helpful given the system-impacting nature suggested by the description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents all three parameters. The description adds no additional parameter semantics beyond what's in the schema descriptions (backendId from list_backends, optional URL override, cache bypass). Baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Load or refresh') and resource ('OpenAPI spec from a URL'), distinguishing it from sibling tools like list_backends or get_endpoint_contract. It explicitly mentions the primary use case for initialization or recovery when 'tools fail because docs path changed'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to use this tool ('Use this first if tools fail because docs path changed'), establishing it as an initialization or recovery step. It implies alternatives by referencing potential tool failures, though it doesn't name specific sibling tools as direct alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

propose_new_endpointB

Create a best-effort endpoint + DTO proposal aligned with deterministic patterns found in the current OpenAPI spec.

ParametersJSON Schema
NameRequiredDescriptionDefault
backendIdYesRequired backend id from list_backends.
resourceYesBusiness resource name, e.g. pet, order, invoice.
actionYesEndpoint action pattern.
customActionNameNoRequired when action=custom.
includePaginationNoAdd page/size params for list action.
specUrlNoOptional docs URL override for this call.

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It states 'best-effort' which hints at non-guaranteed results, but doesn't disclose critical behavioral traits like whether this is a read-only analysis or actually modifies the backend, what 'proposal' entails (e.g., returns structured data, generates code), error handling, or any rate limits. For a tool with no annotations and potentially complex behavior, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core purpose without unnecessary details. It avoids repetition of parameter info already in the schema. However, it could be slightly more structured by explicitly separating endpoint and DTO aspects, but overall it's appropriately sized with zero waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations, no output schema, and a tool that likely involves complex proposal generation (implied by 'best-effort' and pattern analysis), the description is incomplete. It doesn't explain what the output looks like (e.g., a JSON proposal, code snippets), success/failure conditions, or how it interfaces with the backend. For a 6-parameter tool with no structured output documentation, this leaves too many gaps for effective agent use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 6 parameters thoroughly. The description adds no additional meaning beyond what the schema provides—it doesn't explain how parameters interact (e.g., backendId's role) or clarify semantics like 'deterministic patterns.' With high schema coverage, the baseline 3 is appropriate as the description doesn't compensate but also doesn't detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool creates a 'best-effort endpoint + DTO proposal' based on patterns in an OpenAPI spec, specifying both the action (create proposal) and resource (endpoint/DTO). It distinguishes from siblings like list_backends or get_endpoint_contract by focusing on proposal generation rather than listing or retrieving existing data. However, it doesn't explicitly contrast with generate_typescript_dto, which might have overlapping DTO-related functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when needing to propose new endpoints aligned with existing patterns, but provides no explicit guidance on when to use this vs. alternatives like generate_typescript_dto or get_endpoint_contract. It mentions 'deterministic patterns found in the current OpenAPI spec' which suggests context, but lacks clear when/when-not rules or prerequisites beyond what the parameters imply.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 6 tool updatesv0.1.0
    • First observedgenerate_typescript_dto
    • First observedget_endpoint_contract
    • First observedlist_api_endpoints
    • First observedlist_backends
    • First observedload_openapi_spec
    • First observedpropose_new_endpoint
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 6 tools

Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: generate_typescript_dto creates TypeScript types, get_endpoint_contract retrieves endpoint details, list_api_endpoints lists endpoints, list_backends lists backends, load_openapi_spec loads specs, and propose_new_endpoint proposes new endpoints. The descriptions make it easy to differentiate their functions.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern using snake_case: generate_typescript_dto, get_endpoint_contract, list_api_endpoints, list_backends, load_openapi_spec, and propose_new_endpoint. This uniformity makes the tool set predictable and easy to navigate.

Tool Count5/5

With 6 tools, the count is well-scoped for an OpenAPI-focused server, covering core operations like loading specs, listing endpoints and backends, generating types, and proposing new endpoints. Each tool earns its place without feeling excessive or insufficient.

Completeness4/5

The tool set provides strong coverage for OpenAPI workflows, including loading specs, listing endpoints/backends, generating DTOs, and proposing new endpoints. A minor gap exists in lacking direct update or delete operations for endpoints or backends, but agents can work around this given the server's focus on analysis and generation.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • mcp-openapi-schema

    hannesj
    A
    license
    Not graded
    quality
    F
    maintenance
    A MCP server that exposes OpenAPI schema information to LLMs like Claude. This server allows an LLM to explore and understand large OpenAPI schemas through a set of specialized tools, without needing to load the whole schema into the context
    48 npm
    49
    MIT

  • MCP OpenAPI Server

    ReAPI-com
    A
    license
    B
    quality
    D
    maintenance
    A Model Context Protocol server that loads multiple OpenAPI specifications and exposes them to LLM-powered IDE integrations, enabling AI to understand and work with your APIs directly in development tools like Cursor.
    7
    49 npm
    90
    MIT