Dale a tu agente de IA los datos de migración post-cuántica que siempre adivina mal.
Seis herramientas sobre MCP: tamaños de credenciales, recuentos de fragmentos, la ventana de reensamblaje, la taxonomía de fallos de 39 familias y la puntuación de benchmarks. Pregunta a Claude "¿caberá nuestro handshake ML-KEM-768 en una MTU BLE?" y calcula la respuesta en lugar de estimarla.
📖 Documentación completa, tutorial y guía conceptual: https://nickharris808.github.io/pqc-toolkit/
Los agentes están haciendo cada vez más trabajo de migración PQC, y se equivocan con total seguridad en exactamente las cosas que importan: cuán grande es realmente una credencial, en cuántos fragmentos se convierte, y si existe un límite seguro de reensamblaje en tu concurrencia. Eso es aritmética, no criterio — así que dale al agente la aritmética.
La capa de protocolo aquí no tiene dependencias. MCP es JSON-RPC 2.0 sobre stdio delimitado por líneas, que es lo suficientemente pequeño como para implementarlo directamente y mantiene la instalación trivial.
Related MCP server: attestix
pip install git+https://github.com/nickharris808/pqc-migration-mcpEsto también extrae pqc-sizes y pqc-mfb de sus repositorios. Aún no están en PyPI, así que pip install pqc-migration-mcp no funciona hoy.
# talk to it directly -- it is line-delimited JSON-RPC on stdio
echo '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | pqc-migration-mcpAñade a claude_desktop_config.json:
{
"mcpServers": {
"pqc-migration": {
"command": "pqc-migration-mcp"
}
}
}Reinicia Claude Desktop. Las seis herramientas aparecen bajo el conector.
Herramienta | Respuestas |
| ¿Cuántos bytes tiene una credencial KEM+firma, componente por componente? |
| ¿Cuántos fragmentos en este transporte — y es ahora obligatoria la fragmentación? |
| ¿Existe un límite de capacidad seguro? Si no, ¿qué concurrencia funcionaría? |
| Las 39 familias de fallos, con recuentos de casos y análogos publicados |
| ¿Qué se rompe en esta familia, en qué diseños, y qué hizo cada uno? |
| Puntúa un envío PQC-MFB: cobertura, regresiones, familias con cobertura cero |
El transporte es JSON delimitado por líneas — un objeto completo por línea. Mantén la solicitud en una sola línea; una solicitud dividida en dos líneas llega como dos incompletas y devuelve dos errores de análisis -32700.
$ echo '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"reassembly_window","arguments":{"largest_legitimate_object":12000,"memory_budget":32768,"concurrency":3}}}' | pqc-migration-mcpEl servidor responde con un objeto JSON por línea. Con formato bonito, la carga útil content de esa respuesta es:
{
"budget": 32768,
"ceiling": 10922,
"concurrency": 3,
"explanation": "EMPTY WINDOW: floor 12,000 B > ceiling 10,922 B (short by 1,078 B). No capacity cap is both feasible and safe. Raise the budget to at least 36,000 B, reduce concurrency to at most 2, or choose a smaller credential.",
"floor": 12000,
"is_empty": true,
"max_safe_concurrency": 2,
"recommended_cap": null
}El agente recibe un veredicto y el número que lo arreglaría, para que pueda proponer un cambio concreto en lugar de informar de un problema.
Expone detección. No expone reparaciones.
Un agente puede aprender que un diseño falla krack_retransmission y exactamente lo que hizo el diseño sin reparar. No puede obtener el mecanismo que lo cierra. Ese límite es deliberado: una herramienta MCP que devolviera reparaciones permitiría a cualquier usuario enumerar todo el conjunto cerrado en una tarde.
Hay una prueba que llama a describe_family para las 39 familias además de a todas las demás herramientas, concatena las respuestas, y falla si repair_mechanism, repaired_detail o repaired_held aparece en cualquier parte de la salida.
Los errores de dominio — un algoritmo desconocido, una familia desconocida — vuelven como resultado de herramienta con isError: true y un mensaje que nombra las opciones válidas, para que el agente pueda corregirse. Solo los fallos de protocolo se convierten en errores JSON-RPC (-32601 método/herramienta desconocido, -32602 argumentos incorrectos, -32700 línea no analizable).
Una línea malformada no mata el bucle; el servidor responde con un error de análisis y sigue sirviendo.
pip install -e ".[dev]" && pytest # 57 passedLas pruebas cubren el protocolo, cada herramienta, el límite del foso, y el transporte stdio real ejecutado como subproceso — incluyendo una comprobación de que stderr permanece vacío, ya que los clientes MCP leen stdout como protocolo y las advertencias sueltas los confunden.
Aritmética, consulta de taxonomía y puntuación. Sin criptografía, sin red, sin telemetría. No inspecciona tu implementación. Una respuesta limpia significa que tu configuración es sólida, no que tu código la haga cumplir.
pqc-sizes · pqc-mfb ·
pqc-guard-action · pqc-dos-embedded
Cerrar las 39 familias es lo que hace el núcleo cerrado. La materia relevante está cubierta por una solicitud de patente provisional presentada. Para uso comercial del paquete completo, abre una Discusión de GitHub o un issue en este repositorio.
Lo que esto demuestra. Que la aritmética y la taxonomía con las que un agente está razonando son correctas: tamaños de credenciales reales, recuentos de fragmentos reales, un veredicto de ventana real, y la taxonomía de fallos real.
Lo que NO demuestra.
No que el agente haya usado la respuesta. Esto proporciona hechos; no supervisa lo que se hace con ellos.
No una inspección de tu código. Ninguna herramienta aquí lee tu implementación.
No un canal de reparación. Cada herramienta expone solo detección. Una prueba llama a describe_family para las 39 familias además de a todas las demás herramientas y falla si un campo de reparación aparece en cualquier parte de la salida.
Errores. Los problemas de dominio vuelven como resultados de herramienta con isError: true y un mensaje que nombra opciones válidas, para que un agente pueda autocorregirse. Solo los fallos de protocolo se convierten en errores JSON-RPC.
Once herramientas gratuitas para equipos que mueven el intercambio de claves autenticado a post-cuántico. Encuentran y miden; no reparan.
Herramienta | Qué hace | Dónde |
Tamaños, recuentos de fragmentos y la ventana de reensamblaje de dos lados | fuente | |
La misma aritmética para Node y el navegador | fuente | |
Falla la compilación cuando la ventana está vacía | GitHub Action | |
169 líneas de C: el fallo en un dispositivo real de 64 KB | fuente | |
Re-verifica el límite en el dispositivo, sin solucionador SMT | fuente | |
El mismo límite en Lean 4 — 0 | fuente | |
La puerta en RTL sintetizable, 5 pruebas Yosys | fuente | |
pqc-migration-mcp ← estás aquí | Seis herramientas MCP para agentes de IA | fuente |
322 casos · 39 familias de fallos · puntuador | fuente | |
El benchmark como conjunto de datos | HF | |
122 resultados formales nombrados, 6 demostradores | HF | |
Pruébalo en tu navegador, sin instalación | HF Space |
¿Nuevo aquí? El tutorial de principio a fin recorre una migración realista a través de todos ellos en unos diez minutos: tamaños -> ventana -> puerta de CI -> benchmark.
¿Tienes prisa? pqc-sizes te dice en cinco segundos si tu credencial se fragmenta y si existe un límite seguro. pqc-explorer hace lo mismo en un navegador, sin instalación.
Cerrar las 39 familias de fallos — vinculación de degradación, instalación segura contra retransmisiones, transcripciones de fragmentación, secreto hacia adelante en roaming, separación de claves multi-enlace, control de admisión, vinculación de claves de grupo — es un código propietario separado. La materia relevante está cubierta por una solicitud de patente provisional presentada.
Esa división está medida, no afirmada: bajo un control de ruido replicado solo 4 de 32 mecanismos de reparación son distinguibles externamente, por lo que publicar estos detectores no revela las reparaciones.
Para licencias comerciales, abre una Discusión de GitHub o un issue en cualquiera de estos repos.
Apache-2.0. Consulta LICENSE y CONTRIBUTING.md.
Total on-wire bytes for a KEM + signature credential, with a per-component breakdown.
| Name | Required | Description | Default |
|---|---|---|---|
| kem | No | KEM name, e.g. ML-KEM-768 | ML-KEM-768 |
| sig | No | Signature name, e.g. ML-DSA-65 | ML-DSA-65 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It mentions a 'per-component breakdown' but does not specify the output format, side effects, or constraints like required permissions. Minimal disclosure.
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?
A single sentence that efficiently conveys the core function. However, front-loading could be improved by adding an explicit verb. Still well-structured.
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?
Adequate for a simple tool with two optional parameters, but lacks details on the return value format (e.g., boolean? object?). Without an output schema, more context would help.
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 descriptions for both parameters. The description repeats the concept but adds no new meaning beyond what the schema provides. Baseline 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 clearly states the tool computes on-wire bytes for a credential with a breakdown, which distinguishes it from sibling tools like list_failure_families. However, the verb is implied rather than explicit (e.g., 'calculate').
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, when not to, or alternatives. The sibling tools are unrelated, but the description does not help the agent decide context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Detail for one failure family: the invariants it breaks, the unrepaired designs that fail it, and what each did. Does not return repairs.
| Name | Required | Description | Default |
|---|---|---|---|
| family | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist. Description mentions what is returned and what is not (repairs), but lacks information on side effects, permissions, or whether it is a read-only operation. Basic disclosure but not comprehensive.
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?
Single sentence, efficient and front-loaded with purpose. No redundant words, but a structured list of what is included might improve clarity without expanding length significantly.
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?
Describes output content (invariants, designs) but not structure or format. No output schema. Lacks guidance on the parameter value. Adequate for narrow use but insufficient for full autonomy.
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 0% for the only parameter 'family'. Description does not explain what the parameter value should be (e.g., family ID or name) or provide format examples. Fails to add meaning beyond the schema's type and required status.
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?
Description clearly states the tool provides detailed information for one failure family, including invariants and unrepaired designs, and explicitly excludes repairs. This distinguishes it from sibling tool list_failure_families, which likely lists all families.
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?
Implies use when details on a specific family are needed, but does not explicitly state when to use versus siblings like list_failure_families or other tools. No alternatives or exclusions provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
How many fragments an object becomes on a transport, and whether fragmentation is therefore mandatory.
| Name | Required | Description | Default |
|---|---|---|---|
| object_bytes | Yes | ||
| frame_payload | Yes | usable payload bytes per frame |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must carry the full burden of behavioral disclosure. It indicates the tool calculates fragment count and mandatory status, but it does not disclose side effects, authorization needs, error conditions, or whether the operation is read-only. For a computation tool, the lack of safety information is a gap.
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 a single, concise sentence that immediately conveys the tool's purpose with no extraneous words. It is well-structured and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple 2-parameter tool, the description tells what the tool computes, but it lacks information about the return format (the output schema is absent). The agent must infer whether the result is a number, boolean, or structured object. This is a moderate completeness gap.
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 only 50% (frame_payload has a description). The tool description adds context by relating the parameters to object transport, but it does not explain what object_bytes is or provide details beyond the schema. It fails to compensate for the missing schema description of object_bytes.
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 that the tool computes 'how many fragments an object becomes on a transport' and determines if fragmentation is mandatory. This is a specific verb+resource that distinguishes it from sibling tools like list_failure_families and reassembly_window.
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 given on when to use this tool versus alternatives. The description does not mention prerequisites, exclusions, or comparisons with sibling tools. The agent must guess the appropriate context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
All 39 post-quantum migration failure families, with case counts and published prior-art analogues.
| Name | Required | Description | Default |
|---|---|---|---|
No 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 output content but doesn't disclose behavioral traits such as read-only nature, permissions needed, rate limits, or any side effects. For a tool with no annotations, this is insufficient.
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?
A single, clear sentence with no extraneous information. Every word adds value.
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 no output schema, the description provides reasonable context about return values (case counts, analogues). However, it lacks details like ordering, filtering, or any prerequisites. With no annotations, additional behavioral context would improve completeness.
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 are 0 parameters, so the schema provides no information. The description adds meaning by explaining what the tool returns, which is the full list. Baseline for 0 params is 4.
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 specifies the verb 'list' and resource 'failure families', explicitly states 'All 39', and includes details on return content (case counts and prior-art analogues). This distinguishes it from sibling tools like 'describe_family' which likely focuses on one family.
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 use case: get a comprehensive list of all failure families. It doesn't explicitly state when not to use or name alternatives, but the contrast with 'describe_family' is clear. No explicit exclusions or when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The two-sided reassembly-capacity window. Returns is_empty=true when NO capacity cap is both feasible and safe, plus the maximum concurrency that would be safe.
| Name | Required | Description | Default |
|---|---|---|---|
| concurrency | Yes | ||
| memory_budget | Yes | ||
| largest_legitimate_object | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not fully disclose behavior. It lacks information on side effects, authentication, safety, or what 'feasible and safe' means. The description is insufficient for an agent to understand the tool's full behavior.
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 brief with one sentence, but it could be more structured. It front-loads jargon and then specifies returns. No superfluous words, but clarity is sacrificed 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?
With no output schema, the description only partially describes the return value (is_empty and max concurrency). It does not cover error conditions, edge cases, or other potential return fields. The description is incomplete for effective use.
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 has no descriptions, and the tool's description does not explain the meaning of each parameter ('largest_legitimate_object', 'memory_budget', 'concurrency'). Minimal context is provided, leaving the agent guessing.
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 gives a basic idea of the tool's purpose (computing a capacity window), but uses jargon ('two-sided reassembly-capacity window') and doesn't clearly state the action (e.g., 'compute' or 'get'). The return values are specified, providing some clarity.
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 its siblings. The description does not mention context, prerequisites, or alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Score a PQC-MFB submission ({case_id: bool}). Returns coverage, regressions, and which families have zero coverage.
| Name | Required | Description | Default |
|---|---|---|---|
| submission | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses return values (coverage, regressions, zero-coverage families) but does not mention side effects, required authentication, or whether the operation is read-only. Since no annotations are provided, the description bears full burden, and the lack of side-effect clarity is a gap.
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 a single concise sentence that front-loads the verb and resource. However, the notation '{case_id: bool}' is somewhat cryptic and could be integrated into the schema or clarified.
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 lack of output schema and detailed input schema, the description should provide more context on the input object structure and the exact format of the return values. It covers outputs but omits input details, making it incomplete for proper use.
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 has 0% description coverage, and the description only hints at a 'case_id' field via '{case_id: bool}', which is not defined in the schema. The structure of the required 'submission' object is left entirely unexplained, so the description adds minimal value beyond the schema.
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 action (score) and the specific resource (PQC-MFB submission), and lists the outputs (coverage, regressions, zero-coverage families). This distinguishes it from sibling tools like list_failure_families or describe_family, which serve different purposes.
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 the tool is used when you need to evaluate a submission, but it does not provide explicit guidance on when to use it vs. siblings, nor does it mention prerequisites or avoidance scenarios.
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.
v0.1.0credential_sizedescribe_familyfragmentslist_failure_familiesreassembly_windowscore_submissionScored across 6 tools
Each tool targets a distinct aspect of PQC migration analysis: failure families, reassembly capacity, submission scoring, credential size, family details, and fragmentation. No overlaps in functionality.
Most tools follow a verb_noun pattern with underscores (list_failure_families, score_submission, describe_family). 'credential_size' and 'reassembly_window' are noun-like but still clear; 'fragments' is a single noun, slightly deviating.
The set includes 6 tools, which is well within the ideal 3-15 range. Each tool addresses a specific need without redundancy, making the scope manageable and focused.
The tools cover querying failure families and scoring submissions, but lack submission management, repair retrieval (noted in describe_family), and listing submissions. Some gaps exist for a full workflow.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Production-grade cryptography toolkit with 31 MCP tools for classical, PQC, and KMS workflows.
QuantumOracle — 18 post-quantum crypto tools: Kyber, Dilithium, hybrid schemes, migration.
AI-security knowledge as MCP: standards-mapped tools (OWASP, NIST, MITRE) for AI agents.
Tamper-evident proof creation and verification for AI agents via MCP, A2A, and REST.