Skip to main content
Glama
flrngel

Fuzzy Memory MCP Server

by flrngel
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Knowledge Graph Memory Server (from official site enhanced with Fuzzy Search)

A basic implementation of persistent memory using a local knowledge graph. This lets Claude remember information about the user across chats. This version has been enhanced with fuse.js to provide fuzzy, semantic searching capabilities.

Instruction prompt. (Add this to your CLAUDE.md or any other related)

Here is an instruction guide for each tool, focusing on best practices for using the knowledge graph effectively.

### A Guide to Using Knowledge Graph Memory

This guide outlines best practices for interacting with your knowledge graph memory. Following these principles will help you build a clean, accurate, and useful memory over time. The core idea is to first **search** for what you know, then **act** to add, update, or remove information.

---

#### **`search_nodes`**

This is your primary tool for discovery. It performs a fuzzy search across all entity names, types, and observations to find relevant information.

*   **Best Practice:** Always search before you create. To avoid creating duplicate entities (e.g., "Jane_Doe" when "Jane_Doe_Dev" already exists), start with a broad search to see what the graph already knows.
*   **Invocation Tip:** Use conceptual queries. You don't need an exact name. A query like "project manager who likes dogs" will effectively search observations across all entities to find the best match. Review the returned `score` to understand the confidence of the match.

---

#### **`create_entities`**

Use this to establish a new person, place, organization, or concept as a node in your graph.

*   **Storage Tip:** Choose a consistent and unique `name` for each entity (e.g., `FirstName_LastName`, `Project_Name`). This name is the permanent identifier.
*   **Invocation Tip:** Create entities with a few core `observations` from the start. An entity is more useful when it's created with initial facts, such as "is a software engineer" or "founded in 2021".

---

#### **`add_observations`**

Use this to add new facts or attributes to an entity that already exists.

*   **Storage Tip:** Keep observations atomic. Each observation should represent a single, discrete fact (e.g., use "Loves hiking" and "Lives in Colorado" as two separate observations, not one). This makes information easier to manage and remove later.
*   **Invocation Tip:** This tool is for enriching existing entities. It will not add duplicate observations, so you can safely call it with a list of facts without worrying about creating redundant entries.

---

#### **`create_relations`**

This tool connects two existing entities with a directed, active-voice relationship (e.g., `Jane_Doe` -> `reports_to` -> `John_Smith`).

*   **Storage Tip:** Ensure both the `from` and `to` entities already exist before creating a relation between them. A relation is meaningless without its nodes.
*   **Invocation Tip:** Use a consistent vocabulary for `relationType` (e.g., always use `works_at`, not a mix of `works_at` and `employed_by`). This makes the graph structure predictable and easier to query.

---

#### **`open_nodes`**

Use this to retrieve one or more entities by their exact name, along with any relations that exist between them.

*   **Best Practice:** Use this when you know the exact name of an entity and want to see its details and local connections. It's more precise than `search_nodes` for targeted lookups.
*   **Invocation Tip:** Before updating or deleting, use `open_nodes` to inspect the entity and its relationships. This helps confirm you are targeting the correct information.

---

#### **`delete_observations`**

This tool removes specific facts from an entity.

*   **Best Practice:** This is the standard way to update an entity when a fact is no longer true (e.g., removing "is learning Spanish" after proficiency is achieved).
*   **Invocation Tip:** You must provide the *exact* text of the observation to be deleted. Use `open_nodes` first to retrieve the exact phrasing if you are unsure.

---

#### **`delete_relations`**

This tool removes a specific connection between two entities, leaving the entities themselves intact.

*   **Best Practice:** Use this to update the graph when a relationship changes. For example, if a person moves to a new team, you would delete their old `reports_to` relation.
*   **Invocation Tip:** To be successful, the call must exactly match the `from` entity, `to` entity, and `relationType` of the stored relation.

---

#### **`delete_entities`**

This is a destructive action that permanently removes an entity and all relations connected to it.

*   **Best Practice:** Be certain before using this tool. Deleting an entity causes a cascading delete of all its connections. If you only want to remove an incorrect fact, use `delete_observations` instead.
*   **Invocation Tip:** The tool will not fail if the entity doesn't exist, so you don't need to check for its existence before calling.

---

#### **`read_graph`**

This tool retrieves the entire knowledge graph—every entity and every relation.

*   **Best Practice:** Use this tool sparingly, as it can return a very large amount of data. It is best suited for offline analysis, debugging, or getting a complete overview of your memory.
*   **Invocation Tip:** For nearly all interactive tasks, prefer the more focused `search_nodes` or `open_nodes` tools for better performance and relevance.

Related MCP server: Knowledge Graph Memory Server

Core Concepts

Entities

Entities are the primary nodes in the knowledge graph. Each entity has:

  • A unique name (identifier)

  • An entity type (e.g., "person", "organization", "event")

  • A list of observations

Example:

{
  "name": "John_Smith",
  "entityType": "person",
  "observations": ["Speaks fluent Spanish"]
}

Relations

Relations define directed connections between entities. They are always stored in active voice and describe how entities interact or relate to each other.

Example:

{
  "from": "John_Smith",
  "to": "Anthropic",
  "relationType": "works_at"
}

Observations

Observations are discrete pieces of information about an entity. They are:

  • Stored as strings

  • Attached to specific entities

  • Can be added or removed independently

  • Should be atomic (one fact per observation)

Example:

{
  "entityName": "John_Smith",
  "observations": [
    "Speaks fluent Spanish",
    "Graduated in 2019",
    "Prefers morning meetings"
  ]
}

API

Tools

  • create_entities

    • Create multiple new entities in the knowledge graph

    • Input: entities (array of objects)

      • Each object contains:

        • name (string): Entity identifier

        • entityType (string): Type classification

        • observations (string[]): Associated observations

    • Ignores entities with existing names

  • create_relations

    • Create multiple new relations between entities

    • Input: relations (array of objects)

      • Each object contains:

        • from (string): Source entity name

        • to (string): Target entity name

        • relationType (string): Relationship type in active voice

    • Skips duplicate relations

  • add_observations

    • Add new observations to existing entities

    • Input: observations (array of objects)

      • Each object contains:

        • entityName (string): Target entity

        • contents (string[]): New observations to add

    • Returns added observations per entity

    • Fails if entity doesn't exist

  • delete_entities

    • Remove entities and their relations

    • Input: entityNames (string[])

    • Cascading deletion of associated relations

    • Silent operation if entity doesn't exist

  • delete_observations

    • Remove specific observations from entities

    • Input: deletions (array of objects)

      • Each object contains:

        • entityName (string): Target entity

        • observations (string[]): Observations to remove

    • Silent operation if observation doesn't exist

  • delete_relations

    • Remove specific relations from the graph

    • Input: relations (array of objects)

      • Each object contains:

        • from (string): Source entity name

        • to (string): Target entity name

        • relationType (string): Relationship type

    • Silent operation if relation doesn't exist

  • read_graph

    • Read the entire knowledge graph

    • No input required

    • Returns complete graph structure with all entities and relations

  • search_nodes

    • Performs a fuzzy semantic search for nodes in the knowledge graph using Fuse.js

    • Input: query (string)

    • Searches across:

      • Entity names

      • Entity types

      • Observation content

    • Returns an array of search results, each containing:

      • entity: The matched entity object

      • score: Confidence score from 0.0 to 1.0 (higher is better)

    • Uses fuzzy matching with:

      • Threshold: 0.6 (0.0 = perfect match, 1.0 = matches anything)

      • Minimum match character length: 2

      • Location-independent matching

  • open_nodes

    • Retrieve specific nodes by name

    • Input: names (string[])

    • Returns:

      • Requested entities

      • Relations between requested entities

    • Silently skips non-existent nodes

Usage with Claude Desktop

Setup

Add this to your claude_desktop_config.json:

NPX

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "github:flrngel/fuzzy-memory-mcp#main"
      ]
    }
  }
}

NPX with custom setting

The server can be configured using the following environment variables:

{
  "mcpServers": {
    "memory": {
      "command": "npx",
      "args": [
        "-y",
        "github:flrngel/fuzzy-memory-mcp#main"
      ],
      "env": {
        "MEMORY_FILE_PATH": "/path/to/custom/memory.json"
      }
    }
  }
}

  • MEMORY_FILE_PATH: Path to the memory storage JSON file (default: memory.json in the server directory)

VS Code Installation Instructions

For quick installation, use one of the one-click installation buttons below:

Install with NPX in VS Code Install with NPX in VS Code Insiders

Install with Docker in VS Code Install with Docker in VS Code Insiders

For manual installation, add the following JSON block to your User Settings (JSON) file in VS Code. You can do this by pressing Ctrl + Shift + P and typing Preferences: Open Settings (JSON).

Optionally, you can add it to a file called .vscode/mcp.json in your workspace. This will allow you to share the configuration with others.

Note that the mcp key is not needed in the .vscode/mcp.json file.

NPX

{
  "mcp": {
    "servers": {
      "memory": {
        "command": "npx",
        "args": [
          "-y",
          "github:flrngel/fuzzy-memory-mcp#main"
        ]
      }
    }
  }
}

System Prompt

The prompt for utilizing memory depends on the use case. Changing the prompt will help the model determine the frequency and types of memories created.

Here is an example prompt for chat personalization. You could use this prompt in the "Custom Instructions" field of a Claude.ai Project. 

Follow these steps for each interaction:

1. User Identification:
   - You should assume that you are interacting with default_user
   - If you have not identified default_user, proactively try to do so.

2. Memory Retrieval:
   - Always begin your chat by saying only "Remembering..." and retrieve all relevant information from your knowledge graph
   - Always refer to your knowledge graph as your "memory"

3. Memory
   - While conversing with the user, be attentive to any new information that falls into these categories:
     a) Basic Identity (age, gender, location, job title, education level, etc.)
     b) Behaviors (interests, habits, etc.)
     c) Preferences (communication style, preferred language, etc.)
     d) Goals (goals, targets, aspirations, etc.)
     e) Relationships (personal and professional relationships up to 3 degrees of separation)

4. Memory Update:
   - If any new information was gathered during the interaction, update your memory as follows:
     a) Create entities for recurring organizations, people, and significant events
     b) Connect them to the current entities using relations
     b) Store facts about them as observations

Building and Development

Prerequisites

  • Node.js and npm

  • Docker (for building the Docker image)

Local Development

If you've cloned this repository and want to run the server locally for development:

  1. Install dependencies (this will include fuse.js for fuzzy searching):

    npm install

  2. Compile and run the server:

    npm start

Building the Docker Image

The Dockerfile handles installing all necessary dependencies.

docker build -t mcp/memory .

License

This MCP server is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

Available Tools

9 tools
add_observationsB

Add new observations to existing entities in the knowledge graph

ParametersJSON Schema
NameRequiredDescriptionDefault
observationsYes

TDQS

B3.3/5.0
Behavior2/5

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

With no annotations provided, the description must disclose behavioral traits on its own. It only states that it adds observations, without detailing whether observations are appended or replaced, what happens if the entity does not exist (e.g., error or auto-creation), or any other side effects. The tool is clearly a write operation, but critical safety and behavior information is missing.

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, concise sentence that immediately conveys the tool's core function. There is no fluff or redundant phrasing, and the primary verb and object are front-loaded. It earns a high score for efficiency.

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 that there are no annotations and no output schema, the description must provide comprehensive context on its own. However, it only gives a high-level statement and lacks necessary details about input requirements, validation, error handling, or effect on existing data. This leaves significant gaps in the agent's understanding of the tool's full behavior.

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

Parameters2/5

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

The schema has zero coverage for the top-level parameter, and the description does not compensate by explaining the parameter structure. Although the nested schema properties describe entityName and contents, the description adds no semantic value beyond the schema, and the agent must rely solely on the schema to understand that observations is an array of objects with those fields. This is insufficient given the low schema coverage.

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 uses a specific verb 'Add' and identifies the resource 'observations' and the target 'existing entities' within the knowledge graph. This clearly distinguishes it from sibling tools like create_entities (which creates entities) and delete_observations (which removes observations), making the tool's purpose unambiguous.

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 that this tool is used when adding observations to existing entities, but it does not explicitly state when to use it over alternatives or provide any comparison with sibling tools. There is no mention of constraints such as 'only for existing entities' or guidance about creating entities first. Thus, the usage context is implied rather than explicitly outlined.

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

create_entitiesB

Create multiple new entities in the knowledge graph

ParametersJSON Schema
NameRequiredDescriptionDefault
entitiesYes

TDQS

B3.1/5.0
Behavior2/5

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 only states that it creates entities, but does not mention potential duplicate handling, overwrite behavior, validation rules, or whether the operation is atomic—information an agent would need for a mutating tool.

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, front-loaded sentence that communicates the core purpose with no filler. It is appropriately concise for a simple tool.

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 absence of annotations, an output schema, and limited schema coverage, the description should offer more context about usage, side effects, or return behavior. It does not, leaving significant gaps for an agent to make assumptions about how the tool behaves.

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

Parameters2/5

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

The schema's top-level 'entities' parameter has no description (coverage 0%), and the tool description does not explain what constitutes an entity (name, type, observations). The description adds no value beyond the bare phrase 'multiple new entities,' failing to compensate for the schema gap.

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 uses a specific verb ('Create') and a specific resource ('multiple new entities in the knowledge graph'), clearly distinguishing this from sibling tools like create_relations and add_observations. It is explicit and unambiguous.

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 does not mention create_relations, add_observations, or any exclusions, leaving the agent to infer selection based solely on the name.

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

create_relationsB

Create multiple new relations between entities in the knowledge graph. Relations should be in active voice

ParametersJSON Schema
NameRequiredDescriptionDefault
relationsYes

TDQS

B3.3/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It only states 'create' and offers an active-voice guideline, but does not mention idempotency, validation of from/to entities, behavior on duplicates, or error handling.

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 sentence with a brief second clause. Every word earns its place and the main purpose is front-loaded.

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?

For a mutation tool with no annotations or output schema, the description is too sparse. It omits critical details such as whether from/to entities must already exist, how duplicates are handled, and whether creation is atomic for the batch.

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

Parameters2/5

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

Schema description coverage is 0% at the top level, so the description needed to compensate. It adds the active-voice guideline but does not explain the structure of the relations array or the meaning of from/to/relationType, which the schema already partially covers.

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 action (create), the object (multiple new relations), and the context (knowledge graph). It distinguishes from siblings like delete_relations and create_entities.

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 this tool is for creating relations, but it does not explicitly state when to use it versus alternatives or mention any prerequisites. The active-voice guideline is a style note, not usage guidance.

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

delete_entitiesA

Delete multiple entities and their associated relations from the knowledge graph

ParametersJSON Schema
NameRequiredDescriptionDefault
entityNamesYesAn array of entity names to delete

TDQS

A3.5/5.0
Behavior3/5

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 does disclose that associated relations are deleted as part of the operation, which is a useful behavioral detail. However, it does not mention irreversibility, permissions, or whether observations are affected, leaving gaps in transparency.

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 concise sentence that front-loads the action and scope with no unnecessary words. Every word contributes to understanding the tool's purpose.

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 simple one-parameter destructive tool with no output schema, the description conveys the core purpose but omits behavioral details such as error handling, atomicity, and return values. Given the lack of annotations, it is moderately complete but has room for improvement.

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?

The input schema has 100% coverage of the parameter 'entityNames' with a description, so the baseline is 3. The tool description does not add any additional parameter semantics beyond what the schema already provides.

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 tool deletes multiple entities and their associated relations, using a specific verb ('Delete') and resource ('entities' and 'relations'). It distinguishes itself from sibling tools like delete_relations, which only handle relations, and delete_observations, which handles observations.

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 such as delete_relations or delete_observations. It does not state any exclusions, prerequisites, or scenarios where another tool would be more appropriate.

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

delete_observationsB

Delete specific observations from entities in the knowledge graph

ParametersJSON Schema
NameRequiredDescriptionDefault
deletionsYes

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 must disclose behavioral traits. It only states the action without mentioning permanence, side effects, required permissions, or return format. As a mutation tool, 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.

Conciseness5/5

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

The description is a single sentence that directly conveys the core action, with no unnecessary 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.

Completeness2/5

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

The tool has a non-trivial parameter schema and no output schema or annotations. The description is too minimal to fully inform usage, lacking details on how to specify deletions and what to expect in response.

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

Parameters2/5

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

The description does not explain the 'deletions' parameter structure. Schema coverage is 0% for the top-level parameter, and the description adds no semantic meaning beyond the schema's nested field descriptions.

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 function: deleting specific observations from entities in a knowledge graph. It distinguishes itself from sibling tools like delete_entities and add_observations by specifying the granularity ('specific observations').

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?

No guidance on when to use this tool versus alternatives such as delete_entities or when not to use it. The description lacks any context or conditions for usage.

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

delete_relationsA

Delete multiple relations from the knowledge graph

ParametersJSON Schema
NameRequiredDescriptionDefault
relationsYesAn array of relations to delete

TDQS

A3.5/5.0
Behavior2/5

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

With no annotations, the description must convey behavioral traits, but it only says 'Delete' without mentioning consequences such as irreversibility, partial failure handling, or permissions. For a mutating operation, 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.

Conciseness5/5

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

The description is a single sentence that is direct and front-loaded. Every word earns its place, and there is no redundant information.

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?

The tool is simple with one well-specified parameter and no output schema, so the core purpose is covered. However, behavioral details like error handling, atomicity, or effects on related entities are absent, which leaves some ambiguity for an agent.

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?

The input schema fully describes the 'relations' parameter and its nested properties (from, to, relationType), so the description adds little beyond what is already structured. The phrase 'multiple' aligns with the array type but does not provide extra meaning.

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 a specific action ('Delete') on a specific resource ('relations'), and the plural 'multiple relations' distinguishes this from sibling tools like delete_entities and delete_observations. It is concise and unambiguous.

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 for deleting one or more relations, but it does not explicitly state when to prefer this over alternatives, nor does it mention any exclusions or prerequisites. It provides only minimal contextual guidance.

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

open_nodesC

Open specific nodes in the knowledge graph by their names

ParametersJSON Schema
NameRequiredDescriptionDefault
namesYesAn array of entity names to retrieve

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations, the description carries the full burden of disclosing behavior. It only says 'open', which implies read-only retrieval, but does not explicitly state that it is non-mutating, what it returns, or how missing names are handled. This leaves significant ambiguity.

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, efficiently worded sentence that directly states the action and resource. It contains no filler or redundant information.

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?

The tool has no output schema and the description does not clarify what 'open' returns (e.g., node attributes, observations, relations). For an agent to invoke the tool and interpret results correctly, this missing information is a notable gap.

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?

The input schema has 100% coverage, already describing 'names' as 'An array of entity names to retrieve'. The tool description merely restates 'by their names', adding no extra semantic detail beyond the schema, so the baseline of 3 applies.

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 uses the specific verb 'Open' and identifies the resource 'nodes in the knowledge graph', scoped by 'names', making it clear this is a direct retrieval by exact names. It implicitly differentiates from search_nodes (searching) and read_graph (full graph), but does not explicitly name alternatives.

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?

No guidance is given on when to use this tool versus siblings. The description does not state that it should be used when exact node names are known, nor does it exclude using search_nodes for lookup or read_graph for broader context.

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

read_graphB

Read the entire knowledge graph

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?

With no annotations, the description must carry the full burden of behavioral disclosure, but it only states that the graph is read. It does not mention that the operation is read-only, whether it requires permissions, or that the response may be very large. The word 'read' implies non-destructive behavior, but no details are given.

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, concise sentence that directly states the tool's purpose with no redundancy. It is well-structured and every word contributes to the meaning.

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 should explain what reading the graph returns or any caveats (e.g., large payloads). It does not, and it also fails to differentiate this tool from search_nodes for partial reads. The tool is simple, but the description is still incomplete for an agent to use it confidently.

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 tool has zero parameters and the schema is empty, so there is nothing to document. The baseline for zero parameters is 4, and the description correctly indicates that no inputs are needed, without adding unnecessary detail.

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 uses a specific verb 'read' and identifies the resource 'the entire knowledge graph,' clearly distinguishing it from sibling tools that create or delete entities. However, it is brief and doesn't elaborate on the output format or how it differs from export_to_obsidian, so it falls short of 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 explicit guidance on when to use this tool over alternatives like search_nodes or open_nodes. It is only implied that this is for reading the whole graph, with no mention of filtering or use cases.

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

search_nodesA

Performs a fuzzy semantic search for nodes in the knowledge graph based on a query. Returns a list of matching entities, each with a confidence score from 0.0 to 1.0 (higher is better).

ParametersJSON Schema
NameRequiredDescriptionDefault
queryYesThe search query to match against entity names, types, and observation content.

TDQS

A3.5/5.0
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 explains the search is 'fuzzy semantic' and returns confidence scores, which adds useful context. However, it lacks details on permissions, rate limits, pagination, or error handling, which are important for a search operation.

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 two concise sentences with zero waste. It front-loads the purpose and efficiently covers key behavioral aspects (fuzzy semantic search, confidence scores) without unnecessary elaboration.

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 the tool's moderate complexity (search operation with one parameter) and no annotations or output schema, the description is adequate but has gaps. It explains the core functionality and return format but lacks details on error cases, performance, or integration with sibling tools, making it minimally viable.

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 the single 'query' parameter. The description adds minimal value by implying the query matches against 'entity names, types, and observation content', but this is redundant with the schema's description. Baseline 3 is appropriate as 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 ('performs a fuzzy semantic search'), the target resource ('nodes in the knowledge graph'), and the scope ('based on a query'). It distinguishes itself from siblings like 'open_nodes' (likely for opening specific nodes) and 'read_graph' (likely for reading the entire graph) by focusing on search functionality.

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 does not mention prerequisites, exclusions, or comparisons to sibling tools like 'open_nodes' or 'read_graph', leaving the agent to infer usage context independently.

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. 9 tool updatesv1.0.0
    • First observedadd_observations
    • First observedcreate_entities
    • First observedcreate_relations
    • First observeddelete_entities
    • First observeddelete_observations
    • First observeddelete_relations
    • First observedopen_nodes
    • First observedread_graph
    • First observedsearch_nodes
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

A3.5/5.0

Scored across 9 tools

Disambiguation5/5

Each tool has a clearly distinct purpose targeting specific operations on the knowledge graph. For example, add_observations vs. delete_observations handle different lifecycle stages, while open_nodes and search_nodes serve distinct access patterns. There is no significant overlap that would cause agent misselection.

Naming Consistency5/5

All tools follow a consistent verb_noun naming pattern using snake_case, such as create_entities, delete_relations, and search_nodes. The naming is predictable and readable throughout the set, with no deviations in style or convention.

Tool Count5/5

With 9 tools, the server is well-scoped for managing a knowledge graph, covering core operations like creation, deletion, reading, and searching. Each tool earns its place without being overly sparse or bloated, fitting typical expectations for this domain.

Completeness4/5

The tool set provides strong coverage for CRUD operations on entities, relations, and observations, along with search and read capabilities. A minor gap exists in update operations (e.g., no update_entities or update_relations), but agents can work around this by deleting and recreating as needed.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers