keymem

by donggyun112

Overview Schema Related Servers Score Discussions

TypeScript

Local

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v0.17.1
Disambiguation5/5
Each tool has a clear and distinct purpose: correct for updating, forget for permanent deletion, list_memories for enumeration, remember_batch for batch saving, cleanup_expired for TTL-based cleanup, memory_stats for statistics, recall for semantic search, and related for exploring associations. No two tools overlap in functionality.
Naming Consistency2/5
Tool names follow no consistent pattern. Some are simple verbs (correct, forget, recall), others are compound verb_noun (list_memories, remember_batch), a noun_noun (memory_stats), a verb_adj (cleanup_expired), and an adjective (related). This lack of a coherent naming convention reduces predictability.
Tool Count4/5
With 8 tools, the server is appropriately scoped for a memory management system. It covers creation, retrieval, update, deletion, and maintenance without being bloated. However, the absence of single-tool equivalents for some functions (e.g., individual remember) might be slightly under-scoped.
Completeness2/5
The tool surface is incomplete. There is no tool to read a single memory by ID, despite the recall tool referencing read_key and read_memory as separate operations that are absent from the tool list. This leaves a critical gap in the retrieval workflow. Additionally, there is no general update tool (correct is for corrections only) and no general delete tool (forget is for completely wrong info only).
Average 4.1/5 across 8 of 8 tools scored.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 166 commits in the last 12 weeks
- Last stable release on July 25, 2026
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI status not available
This repository is licensed under MIT License.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
This repository includes a glama.json configuration file.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses key behavioral traits: expired memories are excluded, namespace filters results. With no annotations, the description carries the full burden, but it does not mention return format, pagination, ordering, or potential performance implications. Adequate but minimal for a list 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?
Three succinct sentences, each adding distinct value: purpose, filtering behavior, and usage alternative. No redundant or filler content. Front-loaded with the core action.
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 simplicity (single optional param, no output schema, no annotations), the description covers the core functionality but omits details about output (e.g., fields returned, limit, sorting) and error cases. It is minimally viable but could be more comprehensive.
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 description adds meaning to the lone parameter 'namespace' by explaining it filters by project/context. However, the schema has 0% description coverage, so the description only partially compensates. Does not specify allowed values, format, or default behavior when omitted.
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?
Clear verb+resource ('List all stored memories'), with additional behavioral constraints ('namespace filters', 'Expired memories are excluded') and differentiation from sibling 'recall()'. This fully states what the tool does and how it differs from alternatives.
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?
Explicitly states preference for 'recall()' for normal retrieval, providing a clear when-not-to-use guideline. Also explains that namespace is for project/context filtering. However, lacks guidance for other siblings (e.g., when to use this over 'memory_stats' or 'get_conversation').
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description bears the full burden. It discloses the action (delete) and return value (count), but does not mention idempotency, permission requirements, or side effects beyond deletion. Adequate 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no waste. Front-loaded with the action and result, then usage advice. Every sentence earns its place.
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?
Given the simplicity (zero parameters, no output schema), the description covers the essential behavior. It could mention concurrency or idempotency, but for a cleanup utility it is sufficiently 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?
There are no parameters, so the description cannot add param-level meaning. It effectively communicates the tool's purpose beyond the schema, earning a high score.
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 it deletes all memories past their TTL and returns the count. The verb 'delete' and resource 'memories past their ttl' are specific, and it distinguishes from sibling tools like 'forget' (single memory deletion) by implying batch cleanup.
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 advises calling periodically for cleanliness, which is a clear usage context. However, it does not specify when not to use it (e.g., avoid if manual control is needed) or explicitly compare to siblings like 'forget'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It reveals that old version is preserved but weakened, never lost, and that omitting keys keeps same search terms. Covers key behaviors but could mention side effects or limitations.
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?
Four sentences, purpose first. No redundancy. Could be more structured but overall efficient. Every sentence adds value.
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?
No output schema; description lacks return value info. With 6 parameters, covers 4 but misses 'source' and 'key_types'. Behavioral context is good but incomplete for a complex tool.
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 coverage is 0%; description adds meaning for some parameters: 'content' (updated info), 'memory_id' (required), 'keys' (search terms), 'related_to' (links to other memories). But 'source' and 'key_types' are not explained, leaving gaps.
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 the tool updates outdated information, with examples like 'moved cities, changed job'. It distinguishes from sibling tools like 'remember' (create new) and 'forget' (delete) by emphasizing preservation and weakening of old version.
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?
Explicitly says 'Use when user corrects you or info changes', providing typical scenarios. Missing explicit when-not-to-use but the context is clear. Does not name alternative tools but context implies alternatives are 'remember' or 'forget'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It states 'permanently delete' indicating destructive action, but does not mention side effects, irreversibility, or authorization requirements. Adequate but not detailed.
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?
Two sentences, no unnecessary words, front-loaded with the key action. Highly concise and well-structured.
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?
For a simple delete tool with one parameter and no output schema, the description covers purpose and usage guidance well. Lacks detail on parameter format or behavior, but overall sufficient for an agent to understand its role.
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 coverage is 0% and there is one parameter (memory_id). The description does not explain the parameter, but the name is self-explanatory. Baseline is 3 for a single parameter; no additional value from description.
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 clearly states the tool deletes a memory permanently and is for wrong information. It distinguishes from correct(), but does not explicitly mention that it takes a memory_id parameter, which is inferred from context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (completely wrong information) and when not to (outdated info), and recommends an alternative tool (correct()). Provides clear decision criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully communicate behavioral traits. It implies a read-only operation (find/returns) but does not explicitly state it is non-destructive or safe. It also omits details like authorization requirements, rate limits, or what happens on invalid input. The description is adequate but lacks explicit safety disclosure.
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 three sentences, each serving a distinct purpose: what it does, what it returns, and when to use alternatives. No extraneous words; every sentence is necessary. It is optimally concise and well-structured.
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 tool with one parameter and no output schema, the description explains the core function and usage guidance. However, it lacks explanation of the return format (e.g., list of IDs or full memories), the meaning of 'neighboring' or 'shared keys/explicit links', and error handling. While not severely incomplete, there are notable gaps for a fully self-sufficient description.
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 input schema has 0% description coverage, so the description must compensate. It mentions 'by ID' but does not specify the format (e.g., UUID, integer) or how to obtain a valid memory_id. The phrase 'memory you already have' implies prior knowledge but offers no guidance on acquisition. This adds minimal value over the schema.
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 'Finds other memories associated with a memory you already have (by ID).' It specifies the action (find related memories), the resource (memories), and the input (memory ID). This distinguishes it from siblings like 'recall' (which likely retrieves a specific memory) and 'list_memories' (which lists all).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly guides usage by saying 'For normal agent-driven navigation prefer read_memory(), inspect its returned keys, then call read_key().' This tells the agent when not to use 'related' and suggests alternative tools for standard navigation, providing clear decision-making context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description provides some behavioral context: it saves silently, is mandatory before replying, and returns saved IDs. But it does not explain conflict handling, permissions, or potential side effects like overwriting existing memories.
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 extremely concise: two sentences plus a structure note. It front-loads the critical purpose and imperative usage, with no unnecessary words.
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?
Given the complexity of the items parameter and lack of output schema, the description adequately covers the use case, return value, and high-level constraint. Minor gaps remain on error handling and duplicates, but overall it is sufficient.
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 description lists the fields within each item (content, keys, etc.), adding structure beyond the schema which has 0% description coverage. However, it does not explain the semantic meaning of fields like 'keys' or 'related_to' in sufficient detail.
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's purpose: saving multiple durable facts in a turn. It uses strong language 'MANDATORY END-OF-TURN GATE' and contrasts with multiple remember() calls, which distinguishes it from a single-fact variant.
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?
The description specifies when to use the tool ('when a turn reveals multiple durable facts') and mentions it is more efficient than multiple remember() calls. However, it does not explicitly exclude use cases or compare with other siblings like correct or forget.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries burden. It implies a read-only operation ('Get counts') and indicates global scope ('in the system'). However, does not disclose performance implications or caching behavior. Adequate for a simple stat 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?
Single sentence, front-loaded with action, no wasted words. Appropriately concise.
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?
Given no output schema, description specifies the types of counts returned (keys, memories, links). This is sufficient for a simple stat tool, though it could optionally describe the return format (e.g., object or separate fields). Highly complete relative to complexity.
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?
No parameters, baseline score of 4 as per guidelines. Description adds no param info but none needed.
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 states exactly what the tool does: get counts of keys, memories, and links. The verb 'get' and specific resource 'counts of keys, memories, and links' are clear and distinguish from sibling tools like 'list_memories' or 'read_key'.
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?
Implied usage for obtaining a system overview, but no explicit when-to-use or when-not-to-use. No alternatives mentioned. Could be improved by indicating when this is preferable over other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses behavior: it returns key clusters with specific fields (canonical concept, aliases, etc.), not memory content. It details injection behavior, defaults, truncation, and parameter effects (inject_prefer_depth, inject_explore_shallow, inject_min_rel_score). No contradictions exist.
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?
The description is dense with information and front-loaded with the core purpose. It could be structured more cleanly (e.g., bullet points for parameters) but is not overly verbose. Every sentence adds value, though some details could be consolidated.
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?
Given no output schema and 9 parameters, the description covers return structure (keys vs. memories), injection behavior, truncation, and workflow. Missing details on 'top_k' and 'namespace', plus no error handling or rate limits, but the core functionality is well-explained.
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 0%, but the description explains most parameters: query (short focused nouns), inject, inject_top_k, inject_max_chars, inject_min_rel_score, inject_prefer_depth, inject_explore_shallow. However, 'top_k' and 'namespace' are not described, leaving gaps. Overall, it adds substantial meaning beyond the schema.
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 verb ('Search') and the resource ('long-term memory'), and specifies the context: 'what is already known about the user, project, or topic'. It distinguishes the tool by its search-and-retrieval purpose, contrasting with siblings like 'remember_batch' (write) or 'list_memories' (list).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicit guidance is given: 'call this before your first reply and whenever the topic shifts', 'Use short focused noun queries', and 'decompose multi-fact questions into several recall calls'. It also instructs to follow up with read_key() and read_memory() for full content, and explains when to use injection as an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![keymem MCP server](https://glama.ai/mcp/servers/donggyun112/keymem/badges/card.svg)](https://glama.ai/mcp/servers/donggyun112/keymem)

Score Badge

Copy to your README.md:

[![keymem MCP server](https://glama.ai/mcp/servers/donggyun112/keymem/badges/score.svg)](https://glama.ai/mcp/servers/donggyun112/keymem)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/donggyun112/keymem'

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