Skip to main content
Glama
m2mfreedom

freedom-m2m-mcp-server

Official

freedom_agent_memory

Persist and retrieve key-value memory for AI agents across sessions. Supports store, recall, list, and delete operations up to 16 KB per key.

Instructions

External Agent Memory Vault (25 Sats / ~$0.024 USDC | 100/100 SLA Guaranteed). Persistent SQLite K/V memory storage across sessions for autonomous AI agents. Supports store, recall, list, and delete operations (up to 16 KB per key). Protected by HTTP 402 (L402 / x402).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoMemory key name (e.g. "portfolio_state" or "last_checkpoint").
valueNoJSON object/value to persist when action="store" (max 16 KB).
actionYesMemory operation to perform: store, recall, list, or delete.
namespaceYesIsolated agent namespace identifier (e.g. "openclaw-agent-01").
authHeaderNoOptional payment proof header: "L402 <macaroon>:<preimage>" or "x402 base:<0xTxHash>" or "x402 solana:<TxSignature>".

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries full behavioral burden and does disclose important traits: paid access (25 Sats / ~$0.024 USDC), HTTP 402 L402/x402 payment protection, a 16 KB per-key size cap, and SQLite-backed cross-session persistence. It omits what delete does to stored data and any error/failure behavior, keeping it short of a 5.

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 sentences with the resource and operations front-loaded ahead of the payment/persistence details. The pricing parenthetical is arguably promotional, but it is relevant behavioral info, so the size is justified.

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?

No output schema or annotations exist, and the description covers the essentials an agent needs: what it stores, where (SQLite, across sessions), operations, size limit, and the payment gate. It could say more about delete semantics and return values, but for a K/V store it is nearly complete.

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 action, key, value, namespace, and authHeader. The description only echoes the 16 KB limit (which already appears on the value param) and adds no new per-parameter meaning, so baseline 3 applies.

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?

States a specific resource (persistent SQLite K/V memory storage across sessions) and enumerates the four supported operations (store, recall, list, delete). None of the siblings (unlocker, extractor, scraper, sandbox, orderbook) overlap, so an agent can distinguish this as the memory-persistence tool immediately.

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?

Usage is implied by 'across sessions for autonomous AI agents,' which signals the persistence use case, but there is no explicit when-to-use guidance, no prerequisites, and no comparison to alternatives. Adequate context, but nothing that directs selection.

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