Skip to main content
Glama
tbranzov

HAOps MCP Server

by tbranzov

haops_read_memory

Read memory for a project, module, or feature. Use eager mode for full context or lazy mode for a compact index envelope to reduce boot context.

Instructions

Read agent memory for a project, module, or feature.

mode="eager" (default): Returns baseText + full log entry bodies. Full project context in one call. mode="lazy" (ADR-027): For entityType=project — returns a compact INDEX envelope: • baseText (already thin) • Architecture doc tree (headers only: title [artifactSlug/sectionSlug]) • ADR index (headers only) • Active work — in-progress modules + features • Log headers only (timestamp · tag · author) — NO bodies Agent then fetches detail on demand via haops_get_doc_section / haops_read_memory(full:true) / haops_rag_query. For entityType=module/feature in lazy mode: falls back to eager (entity baseText is already thin).

Use full=true (eager mode only) to include integrated (historical) log entries. Lazy default can be enabled via HAOPS_MEMORY_LAZY_DEFAULT=true env var on the MCP server.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNoIf true, include all log entries (including integrated ones). Default: false (only pending entries). Applies to eager mode only.
modeNoeager (default): full memory dump. lazy (ADR-027): index envelope — baseText + doc headers + active work + log headers only. Reduces boot context by ~80%. Default is eager unless HAOPS_MEMORY_LAZY_DEFAULT=true is set on the MCP server.
entityIdYesUUID of the entity (use "self" for project-level memory)
entityTypeYesType of entity to read memory for
projectSlugYesThe project slug (URL identifier)
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool returns different data structures based on mode, and that full=true includes historical log entries. However, it does not mention permissions, rate limits, or potential side effects. For a read-only operation, this is adequate but could be more explicit about safety.

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?

The description is front-loaded with the core purpose and structured logically by mode. While it is somewhat lengthy, every sentence adds value, covering edge cases and configuration. Minor redundancy (e.g., repeating default mode) could be trimmed, but overall it is efficient.

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?

With no output schema, the description adequately explains return values for both modes, including the structure of the lazy envelope. It covers all 5 parameters and their interactions. Missing detail on exact data types or response size, but sufficient for an agent to understand what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds significant meaning beyond the schema by explaining how mode and full interact, the structure of lazy output, and the fallback behavior for non-project entities. This justifies a score above baseline.

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 reads agent memory for a project, module, or feature, and distinguishes two modes (eager and lazy) with specific behaviors. The verb 'read' and resource 'memory' are precise, and the description differentiates from siblings by referencing how it relates to haops_get_doc_section and haops_rag_query.

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 explicitly explains when to use each mode: eager for full context, lazy for boot context reduction. It also references sibling tools for on-demand fetching. However, it does not provide explicit when-not-to-use scenarios or compare directly to alternatives like haops_rag_query for context retrieval.

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/tbranzov/haops-mcp-server'

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