Mnemos — memory as a service

mnemos_store

PAID (0.01 USDC). Store a memory in your isolated bi-temporal namespace. Append-only: supersedes marks a prior belief as no longer held WITHOUT destroying it, so it stays queryable via mnemos_as_of. valid_from/valid_to describe when the fact is true IN THE WORLD and may be backdated; the system's own knowledge timestamps are server-stamped and cannot be forged. Returns an x402 quote; requires header X-TENANT-KEY once settled.

Input Schema

TableJSON Schema

Name	Required	Description
`key`	Yes	Stable identifier for this fact (e.g. 'ACME.runway').
`value`	Yes	The memory content (max 6000 chars).
`valid_to`	No	ISO8601 -- when it stopped being true (omit if still true).
`supersedes`	No	memory_id of the prior belief this replaces.
`valid_from`	No	ISO8601 -- when the fact became true in the world.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

TDQS

A4.8/5.0

Behavior5/5

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

With no annotations provided, the description carries the full burden and excels at it. It discloses the cost (PAID 0.01 USDC), the non-destructive nature of supersedes, the distinction between world time and system time, the server-stamped timestamps, and the required X-TENANT-KEY header, all of which are not visible in the schema.

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 dense but every sentence contributes: it starts with the cost, then states the core purpose, and follows with essential behavioral details. It is front-loaded and structured logically, with no redundant content.

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 the tool's complexity (bi-temporal semantics, payment, headers) and the presence of an output schema, the description covers all critical aspects: purpose, cost, append-only behavior, parameter semantics, authentication, and return value. It is sufficiently complete for an agent to select and invoke the tool correctly.

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?

Although schema coverage is 100%, the description adds significant semantic value. It explains the behavioral implications of 'supersedes' (marks prior belief as no longer held without destruction) and clarifies that valid_from/valid_to describe truth in the world, with backdating allowed. This goes beyond the schema's basic 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 tool's function: 'Store a memory in your isolated bi-temporal namespace.' It uses a specific verb and resource, and the detail about append-only and supersedes distinguishes it from sibling tools like mnemos_as_of and mnemos_search, which are query-oriented.

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 provides clear context for when this tool is appropriate (storing memories, updating via supersedes) and even references mnemos_as_of for querying past states, but it does not explicitly list alternative tools or state when not to use this tool. The guidance is implied rather than fully explicit.

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

All Mnemos — memory as a service tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, with memory-specific tools like mnemos_store, mnemos_search, and mnemos_get_context differentiated by their descriptions. The main ambiguity is between mnemos_search and mnemos_get_context, which both retrieve memories but with different output formats, and summarize_demo is a deliberate clone of summarize though clearly marked as a demo.

Naming Consistency2/5

Naming conventions are inconsistent: some tools are prefixed with mnemos_ (mnemos_as_of, mnemos_store) while others use generic verb_noun names (code_review, fact_verify, notarize, summarize). This mix of styles makes it harder to predict functionality from tool names alone.

Tool Count3/5

15 tools sits at the upper boundary of the typical range, but the server is advertised as memory-as-a-service while also offering many unrelated paid services (code review, fact verification, research briefs, summarization, trust checks, embeddings). This breadth makes the tool set feel overweighted and unfocused relative to the server's stated purpose.

Completeness4/5

The memory domain is well covered: provisioning, storing, searching, context retrieval, and bi-temporal reads are all present, with no obvious dead ends. The non-memory tools are single-purpose and do not require additional CRUD operations, so no critical gaps are apparent for their individual tasks.

Resources

Need Help?