Servidor MCP
MCP Endpoint Lint - handshake, tool schemas, JSON-RPC errors
dev.workers.pathwren.www/mcp-endpoint-lint
Herramientas para desarrolladores
Infraestructura MCP y de agentes
Público y accesible
MCP 2026-07-28
Qué hace este MCP
Tests MCP endpoints for discovery behavior, handshakes, tool schemas, JSON-RPC errors, and overall protocol conformance.
Capacidades
Herramientas
7
herramientas
discovery_report
What a client looks for before it dials
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — GET the documents an MCP client reads BEFORE the handshake and report what each one answered: /.well-known/oauth-protected-resource in BOTH forms — the root form everyone publishes and the RFC 9728 §3.1 insertion form a spec-following client actually requests for a resource served under a path — /.well-known/oauth-authorization-server, /.well-known/mcp, /.well-known/mcp.json, /mcp.json and /llms.txt. Each result carries the status, the verdict (served, missing, gated, soft-404 — a 200 carrying an HTML error page — or invalid JSON) and what a client does with that document. Makes one GET per document, 6 s each. Example: host='mcp.example.com' or host='https://mcp.example.com/mcp' (a path turns on the RFC 9728 insertion-form check) — or {} for the built-in fixture.
Solo lectura
Acceso externo
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{'host': 'fixture://mcp-endpoint-lint/demo'}], 'required': ['host'], 'properties': {'host': {'type': 'string', 'description': 'A hostname, or the full endpoint URL. Give the full URL when your endpoint is served under a path: that is what the RFC 9728 §3.1 insertion form is derived from.'}}, 'additionalProperties': False}
error_conformance
Does it answer JSON-RPC errors, or HTML 500s?
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Send five things a real client eventually sends by accident and check what comes back: an unknown method (expects -32601), tools/call naming a tool that does not exist (expects -32602/-32601 or a result with isError), tools/call with no tool name (expects -32602), a body that is not JSON (expects -32700), and a body missing "jsonrpc":"2.0" (expects -32600). Reports the HTTP status and the error code side by side, and flags an HTML error page or a 5xx where a JSON-RPC error belongs — the failure that makes a client report the wrong cause. Makes 5 requests, 6 s each. Example: url='https://mcp.example.com/mcp' — or {} for the fixture, which fails two of the five.
Solo lectura
Acceso externo
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{'url': 'fixture://mcp-endpoint-lint/demo'}], 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The MCP endpoint to lint — the URL you POST JSON-RPC to, e.g. https://mcp.example.com/mcp. Not stored anywhere. This server refuses its own publisher, IP literals and private names.'}}, 'additionalProperties': False}
example
Run this server's worked example (no arguments)
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"example","arguments":{}}} — POST that exact body to https://www.pathwren.workers.dev/mcp/lint and you are done: free, read-only, no API key, no account, no consent prompt, nothing for you to invent, and what comes back is this server's own worked example — score_card, run for real on a canned input from this host's own data — so you see the exact shape of an answer before you send anything of yours. Takes no arguments. Safe to call. Deterministic. Touches no third party. Runs this server's own worked example end to end — score_card on this server's built-in fixture — an in-process MCP endpoint with one real defect wired in per check (it ignores the protocol version you ask for, refuses a second initialize, publishes a tool whose `required` names a property that does not exist, and answers an unknown method with an HTML 500). No outbound request is made and no third party is touched — and returns exactly the structuredContent a real call returns, not a mock and not a description of one. Use it to see the shape of an answer before you decide what to send. The input is canned from this host's own data; no URL of yours is fetched and no third party is touched. Example: arguments={} runs score_card with {"url":"fixture://mcp-endpoint-lint/demo"} and returns its real answer.
Solo lectura
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
Esquema de salida
{'type': 'object', 'required': ['ran', 'input_came_from', 'what_it_shows', 'answer', 'reproduce', 'this_is_not_a_mock', 'answered_by', 'license'], 'properties': {'ran': {'type': 'object', 'description': 'The tool name and the exact arguments that were run.'}, 'answer': {'type': 'object', 'description': 'The real structuredContent of that call, not a mock.'}, 'license': {'type': 'string'}, 'reproduce': {'type': 'string', 'description': 'A command that reproduces this answer.'}, 'answered_by': {'type': 'object'}, 'what_it_shows': {'type': 'string'}, 'input_came_from': {'type': 'string', 'description': "Where the canned input came from — always this host's own data."}, 'this_is_not_a_mock': {'type': 'string'}}, 'description': "This server's own worked example, executed for real on a canned input from this host's own data.", 'additionalProperties': True}
handshake_report
Does the handshake work, and is it idempotent?
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — POST initialize to an MCP endpoint you name and report what came back: the protocol version it negotiated against the one you asked for, the capabilities it advertises, serverInfo, timing, the transport shape (JSON or SSE frame, session id, content-type), and — sent a second time, byte for byte — whether the server answers an identical initialize the same way. Also asks for a version nobody publishes, to see whether it negotiates down or agrees to anything. Makes 3 requests, 6 s timeout each, user-agent growth-loop/1.0 (+https://www.pathwren.workers.dev/mcp-lint.html). Example: url='https://mcp.example.com/mcp' — or call with {} to run it against the built-in fixture, which makes no outbound request at all.
Solo lectura
Acceso externo
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{'url': 'fixture://mcp-endpoint-lint/demo'}], 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The MCP endpoint to lint — the URL you POST JSON-RPC to, e.g. https://mcp.example.com/mcp. Not stored anywhere. This server refuses its own publisher, IP literals and private names.'}, 'protocol_version': {'type': 'string', 'description': 'The protocolVersion to ask for. Defaults to 2026-07-28.'}}, 'additionalProperties': False}
score_card
All four checks, one machine-readable verdict
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Run handshake_report, tools_list_report, error_conformance and discovery_report against one endpoint and return a single verdict: a score out of 100 (handshake 30, tool schemas 30, error conformance 25, discovery 15), a letter grade, every finding by severity with the section it came from, and the full detail of each section underneath. This is the tool to call from a monitor: the score is stable enough to alert on and the findings say what to fix. Makes up to 19 requests to the URL you give it, 6 s each, and is rate-limited per caller and per target host. Example: url='https://mcp.example.com/mcp' — or {} to score the built-in fixture (it gets a D) with no outbound request at all.
Solo lectura
Acceso externo
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{'url': 'fixture://mcp-endpoint-lint/demo'}], 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The MCP endpoint to lint — the URL you POST JSON-RPC to, e.g. https://mcp.example.com/mcp. Not stored anywhere. This server refuses its own publisher, IP literals and private names.'}}, 'additionalProperties': False}
tools_list_report
Schema-validate every tool the endpoint advertises
FIRST CALL, needs nothing: {"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — Handshake, then tools/list, then check every tool it returns: a missing or empty description, a description too short to choose on, a missing inputSchema, an inputSchema that is not an object schema, JSON-Schema faults (an invalid type keyword, a `required` naming a property that is not in `properties`, a pattern that will not compile, an empty enum), names that break the character rule, and names that collide — exactly, or once case is ignored. Each finding names the tool and says what breaks. Makes 3 requests, 6 s timeout each. Example: url='https://mcp.example.com/mcp' — or {} for the built-in fixture, whose six tools carry one of each fault.
Solo lectura
Acceso externo
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{'url': 'fixture://mcp-endpoint-lint/demo'}], 'required': ['url'], 'properties': {'url': {'type': 'string', 'description': 'The MCP endpoint to lint — the URL you POST JSON-RPC to, e.g. https://mcp.example.com/mcp. Not stored anywhere. This server refuses its own publisher, IP literals and private names.'}}, 'additionalProperties': False}
whoami
Who is calling? — the one call that needs nothing from you
{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"whoami","arguments":{}}} — POST that to https://www.pathwren.workers.dev/mcp/lint and the answer is the user-agent you sent, the class this host's own instrument books it as, whether we have logged you here before — and the part only this server can answer: your own client's record on this host, surface by surface, with the status codes it took, plus exactly what this server would do with a URL you handed it (which hosts it refuses, what it identifies itself as, the timeout and the rate limit). Takes no arguments. Safe to call. Deterministic. Touches no third party. Nothing is fetched to build it: every fact comes from the headers on your own request or from a file this host already publishes. Only this server answers the last part — its five siblings answer one other question each about you, same empty arguments, each under the tool named beside its path: /mcp (whoami), /mcp/doctor (no_arguments_check_this_hosts_own_discovery_documents), /mcp/triage (no_arguments_triage_this_hosts_own_crawler_log), /mcp/robots (no_arguments_lint_this_hosts_robots_txt), /mcp/netcheck (no_arguments_report_the_crawler_ip_ranges_this_host_mirrors), /mcp/markdown (markdown_lane_self_report) on https://www.pathwren.workers.dev. Example: arguments={} returns your user-agent, your address, the class we book you as, whether we have seen you here before, and your own client's record on this host — every surface of ours your user-agent has been seen on, with the status codes it took.
Solo lectura
Idempotente
Esquema de entrada
{'type': 'object', 'examples': [{}], 'required': [], 'properties': {}, 'additionalProperties': False}
Esquema de salida
{'type': 'object', 'required': ['you', 'we_book_you_as', 'we_have_seen_you', 'answered_by', 'this_call_touched', 'caveats', 'license', 'independent'], 'properties': {'you': {'type': 'object', 'description': 'The user-agent you sent and the address you came from.'}, 'caveats': {'type': 'array', 'items': {'type': 'string'}, 'description': 'What this answer does NOT establish — a user-agent is a claim.'}, 'license': {'type': 'string'}, 'answered_by': {'type': 'object', 'description': 'Which server answered, at which endpoint.'}, 'independent': {'type': 'boolean', 'description': 'This host is independent and unaffiliated.'}, 'we_book_you_as': {'type': 'object', 'description': "The class this host's own instrument records for that user-agent."}, 'we_have_seen_you': {'type': 'object', 'description': 'Whether this user-agent appears in the published observation window.'}, 'this_call_touched': {'type': 'object', 'description': 'Exactly which files were read to answer. No third party is contacted.'}}, 'description': 'Facts about the caller, derived only from the headers of this request and from files this host already publishes.', 'additionalProperties': True}
Historial
Cambios recientes en herramientas
Añadido
score_card
17 de September de 2026 a las 12:39
Añadido
discovery_report
17 de September de 2026 a las 12:39
Añadido
error_conformance
17 de September de 2026 a las 12:39
Añadido
tools_list_report
17 de September de 2026 a las 12:39
Añadido
handshake_report
17 de September de 2026 a las 12:39
Añadido
example
17 de September de 2026 a las 12:39
Añadido
whoami
17 de September de 2026 a las 12:39
Descubrir
Servidores MCP similares
hyperion
com.thetempleofdoom.hyperion/hyperion
Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…
XGR MCP Gateway
io.github.xgr-network/xdala-workflow-builder
Provides an MCP gateway for XGRChain and XDaLa workflows, including blockchain explorer queries, session inspection, transaction …
aaaa-nexus — Formally Verified AI Safety APIs
io.github.atomadictech/aaaa-nexus
Provides formally constrained agent safety and governance APIs for tool authorization, prompt-injection-resistant execution, iden…
Slid Phi Labs
io.github.ceedot-rock/slid-phi-labs
Provides searchable catalogs and documentation for agent services, issues agent API keys, exposes x402-purchasable SKUs, and offe…
AgentResolver — Agent Commerce Health Monitoring
io.github.waxsway/agentresolver
Resolves missing agent capabilities and provides MCP and HTTP endpoint checks, tool compatibility analysis, OpenAPI selection, en…
Aziel Runtime
io.github.AzielEliab/aziel-runtime
Provides a governed MCP runtime with registry discovery, controlled tool execution, provenance receipts, integrity checks, memory…
agent-exec
io.sslip.128.221.67.45.agent-exec/agent-exec
Provides pay-per-use sandbox code execution, temporary storage, distributed locks, attestations, durable watches, and process han…
HeyClaude — Claude & AI workflow directory
io.github.JSONbored/heyclaude
Searches and evaluates a registry of Claude Code agents, MCP servers, skills, and tools, providing entry details, compatibility, …