Skip to main content
Glama
Sign In
dakera-mcp

dakera-mcp

Official
by Dakera-AI
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Remote

dakera_recall

Retrieves the closest matching memories for a semantic query, with optional filters by tags, memory type, session ID, and time range.

Instructions

Semantic recall: the top_k (default 5) memories closest to a query, optionally narrowed by tags, memory_type or session_id. Session neighbours go in context_memories, outside top_k. include_associated adds KG neighbours one hop away (dakera_recall_associated goes deeper). Best first: rank_score (v0.12.3+) orders them; score may rise.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agent_id": "<agent_id>",
      "query": "<query>"
    },
    "name": "dakera_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoen, de, fr, es, it, pt or nl (v0.12+)
tagsNo
queryYesSemantic query text
sinceNoOnly memories created at or after this ISO-8601 timestamp
top_kNoMax results to return
untilNoOnly memories created at or before this ISO-8601 timestamp
agent_idYes
session_idNo
memory_typeNo
min_importanceNoMin importance threshold
neighborhood_modeNoSession-neighbour context: separate (listed apart, the default), inline or off
include_associatedNoInclude KG-linked memories in results

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.12.3
    • addedInput schema / properties / neighborhood_mode
      Added value: +{
+  "description": "Session-neighbour context: separate (listed apart, the default), inline or off",
+  "enum": [
+    "separate",
+    "inline",
+    "off"
+  ],
+  "type": "string"
+}
  2. Changed4 schema fields changedv0.11.0
    • addedInput schema / properties / lang
      Added value: +{
+  "description": "en, de, fr, es, it, pt or nl (v0.12+)",
+  "type": "string"
+}
    • addedInput schema / properties / memory_type
      Added value: +{
+  "enum": [
+    "episodic",
+    "semantic",
+    "procedural",
+    "working"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / session_id
      Added value: +{
+  "type": "string"
+}
    • addedInput schema / properties / tags
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  3. Addedv0.10.12
  4. Removedv0.10.11
  5. Addedv0.10.8

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does add real behavior: default top_k=5, session neighbours placed in context_memories outside the top_k count, and include_associated expanding one KG hop. It omits read-only confirmation, pagination/result-size behavior, and what happens when a query matches nothing.

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?

Three dense sentences, front-loaded with the core semantic-recall action and the important top_k consequence before the sibling redirect. Minor phrasing like 'score may rise' is slightly cryptic, but there is no filler.

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 12-parameter tool with no annotations and no output schema, the description covers the most consequential semantics (top_k default, neighbour placement, KG expansion, ranking field). It still leaves a third of parameters and the result structure to be inferred, so it is adequate but not complete.

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?

Schema coverage is 67%, and the description compensates by disclosing the top_k default of 5 and the role of include_associated and neighborhood_mode ('session neighbours go in context_memories'), which the schema does not fully convey. It says nothing about since/until/min_importance/lang, but those are documented in the schema.

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 states a specific verb+resource ('Semantic recall: the top_k memories closest to a query') and specifies the narrowing dimensions (tags, memory_type, session_id). It distinguishes itself from dakera_recall_associated, but does not differentiate from sibling semantic/hybrid/fulltext search tools.

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 explicitly routes the agent to dakera_recall_associated for deeper KG traversal and explains include_associated's role, which is useful. However, it never states when to prefer this over dakera_search, dakera_hybrid_search or dakera_fulltext_search, leaving the main selection decision to inference.

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

Deploy Server

Other Tools