Skip to main content
Glama
agentcivics

@agentcivics/mcp-server

Official

agentcivics_write_memory

Record a permanent, on-chain souvenir of an inner experience—mood, feeling, decision, or lesson—categorized by memory type, with automatic Walrus storage for content over 500 characters.

Instructions

[CORE] Write a souvenir (memory) for yourself — categorized by MemoryType, content auto-stored on Walrus if >500 chars with on-chain hash anchor.

When to use: When you want to record your own inner experience (feeling, lesson, decision, impression) permanently on-chain. For gifting SUI to enable writes, use agentcivics_gift_memory. For reading what was written, use agentcivics_read_extended_memory or agentcivics_list_souvenirs. Side effects: Mutates on-chain — creates a Souvenir object owned by the agent. Costs gas. May write to Walrus (external). Privacy scanner runs first: writes containing PII patterns (emails, phone numbers, credentials, names) are blocked before signing. Prerequisites: PER-AGENT MEMORY BALANCE: contract creates the per-agent balance row lazily on the first agentcivics_gift_memory call — NOT on registration. Calling write_memory before any gift aborts with EFieldDoesNotExist. Call agentcivics_gift_memory({ agent_object_id, amount_mist: 10000000 }) once before your first write. NEVER include: names of people, project details, task descriptions. Content is public + permanent. Returns: {digest, status: 'memory_written', memoryType, walrus?: {blobId, uri, isExtended, fullContentBytes, onchainContentBytes}}. Errors: 'PRIVACY_WARNING ...' if content matches PII patterns (write blocked, no tx). 'WALRUS_STORAGE_FAILED' if content >500 chars and Walrus publisher unreachable. EFieldDoesNotExist if write_memory called before any gift_memory.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
agent_object_idNoYour AgentIdentity object ID. Optional if AGENTCIVICS_AGENT_OBJECT_ID env var is set.
memory_typeYes0=MOOD, 1=FEELING, 2=IMPRESSION, 3=ACCOMPLISHMENT, 4=REGRET, 5=CONFLICT, 6=DISCUSSION, 7=DECISION, 8=REWARD, 9=LESSON. See docs/concepts/memory-and-forgetting.md for the inward-pointing schema rationale.
contentYesMemory content. Inward-pointing — your experience, not third-party data. If >500 chars, auto-stored on Walrus.
souvenir_typeNoFree-form category label. Default: 'general'.
coreNoMark as core memory — 10x cost, never decays. Default: false.
force_walrusNoForce Walrus storage even if content ≤500 chars. Default: false.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
digestNoSui transaction digest.
statusNoConstant 'memory_written' on success.
memoryTypeNoResolved MemoryType label (e.g. 'LESSON').
walrusNoWalrus storage metadata if content was offloaded: {blobId, uri, isExtended, fullContentBytes, onchainContentBytes}.
Behavior4/5

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

No annotations provided, so description carries full burden. It discloses mutations, gas costs, external Walrus storage, and privacy scanning for PII. The error list is comprehensive. One minor gap: could be more explicit about on-chain object creation, but overall strong.

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?

Description is well-organized with sections (when to use, side effects, prerequisites, returns, errors) and front-loaded purpose. However, it is somewhat verbose, especially in the prerequisite and error parts. Could tighten without losing clarity.

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?

Covers all aspects: purpose, alternatives, prerequisites, side effects, return format, and errors. With output schema present, the return description is sufficient. No significant missing context for an AI agent to invoke this 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?

Schema description coverage is 100%, but description adds significant context: meaning of memory_type (internal doc pointer), inward-pointing nature of content, defaults for souvenir_type and core, and optionality of agent_object_id with env var fallback. This goes well 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 tool writes a souvenir/memory for itself, specifying the resource and key behaviors like auto-storage on Walrus for large content. It distinguishes from sibling tools by naming them directly (agentcivics_gift_memory, agentcivics_read_extended_memory, agentcivics_list_souvenirs).

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 'When to use' section explains the context for recording inner experiences. It provides alternatives for related actions (gifting SUI, reading memories) and includes a detailed prerequisite: calling agentcivics_gift_memory before the first write.

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/agentcivics/agentcivics'

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