memory-arbiter-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MEMORY_ARBITER_CLIENT | Yes | Client identifier for the tool (e.g., zcode, codex, cursor, claude-code) | |
| MEMORY_ARBITER_DB_PATH | Yes | Path to the shared SQLite database file | |
| MEMORY_ARBITER_AGENT_ID | Yes | Agent identifier for the client (e.g., zcode-default) |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memoryA | Daily Memory Arbiter tool. Use action=remember/find/read/update/judge/status/help. Use remember for new reusable facts, find for active recall, read for a memory by id, update for an existing current/canonical memory, judge for required conflict-judgment receipts, and status for runtime health. If a user says a new document replaces the current source of truth, find/read the existing memory and update it; do not create a duplicate active memory or retire it unless the user explicitly asks for whole-memory retirement. If unsure about fields, call action=help. |
| memory_reviewA | Read-only Memory Arbiter inspection. Use view=overview/doctor/conflicts/conflict_detail/judgments/history/expired/audit/entities/help. This tool never changes memory state. Use it when the user asks to inspect health, conflicts, conflict details, judgment history, memory history, expired memories, audit summaries, or entity coverage. If unsure about fields, call view=help. |
| memory_governA | User-authorized Memory Arbiter governance. Use action=retire/resolve_conflict/confirm/correct_judgment/accept_workspace_alias/reject_workspace_alias/rename_workspace_canonical/migrate_workspace/confirm_pending_workspace/help. Use only for explicit governance decisions. Do not use retire for ordinary updates, partial conflicts, or source-of-truth replacement; use memory(action="update") instead. Retire is only for whole-memory retirement after explicit user authorization. Workspace alias decisions and pending workspace confirmation also belong here. If unsure about fields, call action=help. |
| memory_repairA | Memory Arbiter maintenance and repair. Use task=split/rebuild_claims/rebuild_embeddings/cleanup_history/cleanup_vectors/resync_vectors/set_entity/activate_pending/semantic_control/notice/help. Prefer dry_run first where available. Cleanup, activation, and protected-memory metadata changes still require authorized=true when the underlying operation requires it. This is for maintenance, not fact governance; use memory_govern for user-authorized fact decisions. If unsure about fields, call task=help. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/billy12151/memory-arbiter-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server