Skip to main content
Glama
Kirachon

Context Engine MCP Server

by Kirachon

Add Memory

add_memory

Store important project preferences, decisions, or facts as persistent memories that are automatically retrieved via semantic search in future sessions.

Instructions

Store a memory for future sessions. Memories are persisted as markdown files and automatically retrieved via semantic search when relevant.

Categories:

  • preferences: Coding style, tool preferences, personal workflow choices

  • decisions: Architecture decisions, technology choices, design rationale

  • facts: Project facts, environment info, codebase structure

Examples:

  • Add preference: "Prefers TypeScript strict mode"

  • Add decision: "Chose JWT for authentication because..."

  • Add fact: "API runs on port 3000"

Optional metadata fields improve ranking and traceability across sessions:

  • subtype: finer-grained label such as review_finding or failed_attempt

  • priority: critical, helpful, or archive

  • tags, source, linked_files, linked_plans, evidence, owner, timestamps

Memories are stored in .memories/ directory and indexed for semantic retrieval.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoOptional tags to support filtering and ranking
ownerNoOptional owner for memory maintenance
titleNoOptional title for the memory (useful for decisions)
sourceNoOptional source path or identifier
contentYesThe memory content to store (max 5000 characters)
subtypeNoOptional subtype label (for example: review_finding, failed_attempt, incident)
categoryYesCategory of memory: preferences (coding style), decisions (architecture), or facts (project info)
evidenceNoOptional evidence reference (commands, receipts, or docs)
priorityNoOptional priority used for memory ranking
created_atNoOptional ISO timestamp for when this memory was first created
updated_atNoOptional ISO timestamp for the most recent update
linked_filesNoOptional file paths related to this memory
linked_plansNoOptional plan identifiers related to this memory
Behavior5/5

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

Discloses persistence as markdown files, automatic semantic retrieval, storage directory '.memories/', indexing, and maximum content length (5000 chars). Annotations are minimal, so description carries full burden and does so excellently.

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?

Well-structured with sections (purpose, categories, examples, optional metadata, storage). Front-loaded with core action. Slightly verbose but every section adds value for a parameter-rich tool.

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

Completeness4/5

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

Covers purpose, usage, categories, examples, metadata fields, storage behavior. No output schema, but return type is not critical for a write tool. Could mention success confirmation, but overall 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?

Input schema has 100% coverage, but description adds value by grouping optional metadata fields and explaining their purpose (ranking, traceability). Examples illustrate content and category usage, exceeding baseline of 3.

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?

Description clearly states 'Store a memory for future sessions' with specific verb and resource. Categories and examples further clarify purpose. Distinguishes from sibling 'list_memories' (store vs. list).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides categories and examples guiding appropriate usage. Does not explicitly state when not to use or name alternatives, but context is clear enough for an AI agent.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Kirachon/context-engine'

If you have feedback or need assistance with the MCP directory API, please join our Discord server