Hipocampo MCP

search_hipocampo

Busca en el Hipocampo con carriles estructurados + semánticos.

Es solo lectura (no modifica memorias). Devuelve una salida compacta por
defecto: id, relevancia, code/fecha/nivel, un fragmento corto y el motivo.

Sintaxis de query (opcional, se puede combinar con texto libre):
  code:opencode_session_forensics
  category:infraestructura,trigger:mcp
  nivel:automatica  |  type:decision  |  id:4039  |  #4039
  after:2026-10-01  |  since:7d  |  before:today
  "frase exacta entre comillas"

También acepta filtros por argumentos (code=, categories=, nivel=,
memory_type=, ids=, created_after=, created_before=). Los argumentos
explícitos tienen prioridad sobre la sintaxis de la query.

Args:
    query: Texto libre y/o filtros. Puede ir vacío si se usan filtros.
    session_id: Filtra a una sesión concreta.
    rerank: "auto" (default; re-rankea solo si puede cambiar la decisión),
            "always" (TypeSafe/classifier, acotado) o "never".
            El booleano antiguo se acepta: True≈always, False≈never.
    k: Resultados a devolver (1-20, default 5).
    offset: Paginación (0-based).
    code: Filtro exacto por code.
    categories: Filtro por una o más categorías (coincidencia cualquiera).
    nivel: episodica | semantica | automatica.
    memory_type: event | decision | profile | ...
    ids: Lista de IDs numéricos de memoria_vectorial.
    created_after / created_before: Fechas ISO (YYYY-MM-DD) o "7d"/"today".
    include_pending: Si False, oculta filas cuyo embedding aún no está listo.
    rerank_top_k: Cuántos resultados re-rankear (3-20, default 8).
    rerank_budget_ms: Presupuesto HTTP del re-rank (100-5000 ms, default 800).
    format: "compact" (default), "full" (formato histórico) o "json".
    snippet_chars: Longitud del fragmento (80-2000, default 300).
    include_scores: Muestra el score numérico en la salida compacta.
    explain: Muestra el desglose de canales (vec/lex/struct).

Returns:
    Texto formateado (compact/full) o JSON. Si no hay coincidencias,
    indica que la búsqueda fue válida pero sin resultados.

Input Schema

Name	Required	Default
`k`	No
`ids`	No
`code`	No
`nivel`	No
`query`	No
`format`	No	compact
`offset`	No
`rerank`	No	auto
`explain`	No
`categories`	No
`session_id`	No
`memory_type`	No
`rerank_top_k`	No
`created_after`	No
`snippet_chars`	No
`created_before`	No
`include_scores`	No
`include_pending`	No
`rerank_budget_ms`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed20 schema fields changedOct 20, 2026

addedInput schema / properties / categories

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Categories"
+}

addedInput schema / properties / code

Added value: +{
+  "default": "",
+  "title": "Code",
+  "type": "string"
+}

addedInput schema / properties / created_after

Added value: +{
+  "default": "",
+  "title": "Created After",
+  "type": "string"
+}

addedInput schema / properties / created_before

Added value: +{
+  "default": "",
+  "title": "Created Before",
+  "type": "string"
+}

addedInput schema / properties / explain

Added value: +{
+  "default": false,
+  "title": "Explain",
+  "type": "boolean"
+}

addedInput schema / properties / format

Added value: +{
+  "default": "compact",
+  "title": "Format",
+  "type": "string"
+}

addedInput schema / properties / ids

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "integer"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Ids"
+}

addedInput schema / properties / include_pending

Added value: +{
+  "default": true,
+  "title": "Include Pending",
+  "type": "boolean"
+}

addedInput schema / properties / include_scores

Added value: +{
+  "default": false,
+  "title": "Include Scores",
+  "type": "boolean"
+}

addedInput schema / properties / k

Added value: +{
+  "default": 5,
+  "title": "K",
+  "type": "integer"
+}

addedInput schema / properties / memory_type

Added value: +{
+  "default": "",
+  "title": "Memory Type",
+  "type": "string"
+}

addedInput schema / properties / nivel

Added value: +{
+  "default": "",
+  "title": "Nivel",
+  "type": "string"
+}

addedInput schema / properties / offset

Added value: +{
+  "default": 0,
+  "title": "Offset",
+  "type": "integer"
+}

addedInput schema / properties / query / default
```
Added value: +""
```
changedInput schema / properties / rerank / default
```
Previous value: -falseNew value: +"auto"
```

changedInput schema / properties / rerank / type

Previous value: -"boolean"New value: +"string"

addedInput schema / properties / rerank_budget_ms

Added value: +{
+  "default": 800,
+  "title": "Rerank Budget Ms",
+  "type": "integer"
+}

addedInput schema / properties / rerank_top_k

Added value: +{
+  "default": 8,
+  "title": "Rerank Top K",
+  "type": "integer"
+}

addedInput schema / properties / snippet_chars

Added value: +{
+  "default": 300,
+  "title": "Snippet Chars",
+  "type": "integer"
+}

removedInput schema / required
```
Removed value: -[
-  "query"
-]
```

Changed1 schema field changedOct 17, 2026

addedInput schema / properties / rerank

Added value: +{
+  "default": false,
+  "title": "Rerank",
+  "type": "boolean"
+}

First observedSep 8, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations provided, the description carries the full burden and does well: it declares read-only semantics ('no modifica memorias'), describes the default compact output fields, explains rerank modes (auto/always/never) and the boolean back-compat mapping, and gives budget/limit semantics for rerank. It omits permission or rate-limit considerations, which keeps it short of a 5.

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?

Front-loaded with purpose, then query syntax, then a parameter block — a sensible order for a 19-param tool. There is some duplication (query operators are re-listed as arguments), but for a schema this large the length is justified rather than padded.

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

Completeness5/5

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

Given 19 parameters, no annotations, and an output schema that exists, the description supplies everything the agent needs: purpose, safety profile, query grammar, argument precedence, defaults and ranges, plus a brief note on the no-results case. Nothing material is left undocumented.

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

Parameters5/5

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

Schema coverage is 0%, so the description must compensate fully and it does: the Args block documents all 19 parameters, adds enums (nivel: episodica|semantica|automatica, memory_type, format, rerank), numeric ranges (k 1-20, rerank_top_k 3-20, rerank_budget_ms 100-5000, snippet_chars 80-2000), date formats, and the query mini-syntax with code/category/nivel/after/since/ids operators.

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?

States a specific verb and resource ('Busca en el Hipocampo') and clarifies the mechanism ('carriles estructurados + semánticos'), so the agent knows this is a hybrid structured/semantic search. It does not, however, distinguish itself from the sibling quick_hipocampo_search, so an agent still has to guess which search tool to pick.

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?

It explains that query can be empty when argument filters are used and that explicit arguments take precedence over query syntax, which is genuine usage guidance. But it never says when to use this tool versus quick_hipocampo_search or get_hipocampo, and gives no exclusions or prerequisites beyond the read-only note.

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

All Hipocampo MCP tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?