MemoryGuard
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| memoryguard_context_bootstrapA | Use when starting one new task to build bounded mandatory rules and relevant governed memory context. Do not use for exact record lookup or repeatedly within same task. Uses trusted binding and may mark one pending local CodeGraph receipt consumed. |
| memoryguard_memory_searchA | Use when finding governed memories by text and lifecycle status. Do not use when an exact memory_id is known; use memoryguard_memory_read instead. |
| memoryguard_memory_readA | Use when an exact memory_id is already known and its governed record is needed. Do not use for discovery; use memoryguard_memory_search instead. |
| memoryguard_memory_writeA | Use when user explicitly asks to retain a durable fact, preference, project decision, or procedure. Do not use for raw transcripts or temporary task notes. Writes locally and may organize duplicates or conflicts. |
| memoryguard_memory_updateA | Use when owner must correct body, kind, recall policy, or priority of one known memory. Do not use to create a record, change lifecycle status, or modify another owner's memory. |
| memoryguard_memory_deleteA | Use when owner must remove one known memory from future recall. Do not use for irreversible erasure: this is a local soft-delete recorded as status=deleted. |
| memoryguard_memory_statusA | Use when checking shared-memory availability, bound scope, total and active records, lifecycle and kind counts, and evidence-link count. Do not use to search or read individual memory content. |
| memoryguard_auditA | Use when checking local V2 reference integrity before repair or release. Do not use to read a memory record, modify data, or assess general Agent quality. |
| memoryguard_explainA | Use when a memoryguard_audit finding_id needs its evidence, impact, and suggested repair. Do not use for generic memory lookup or to apply a repair. |
| memoryguard_capabilitiesA | Discover registered MCP operations and every GUI operation with its current headless availability. Reads only V2 manifest state and registry metadata; requires no memory binding or source access. Use operation/query plus offset pagination; request include_schema=true only for a selected page. |
| memoryguard_invokeA | Invoke one explicitly registered MCP operation found through memoryguard_capabilities. Never accepts native handler or GUI method names. Mutating targets require confirmed=true and idempotency_key. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 11 tools
Every tool has a clearly distinct role, and descriptions actively prevent misselection (e.g., memory_read vs memory_search, audit vs explain, capabilities vs invoke). The lifecycle operations also explicitly state what they should not be used for.
All tools share the memoryguard_ prefix and use readable snake_case, with memory operations following a consistent memory_<action> pattern. However, audit, explain, capabilities, invoke, and context_bootstrap deviate from a uniform verb_noun convention, creating minor inconsistency.
Eleven tools is well-scoped for a governed-memory server: CRUD/search/status, audit/explain, context bootstrap, and a capability-discovery/invocation pair. Each tool has a meaningful place and the count feels neither bloated nor thin.
The surface covers memory creation, reading, searching, updating, soft-deletion, status inspection, audit, explanation, and task context bootstrapping. Minor gaps remain around explicit lifecycle transitions (e.g., restore/archive) and applying audit repairs, though the generic invoke tool provides a partial extension path.