Skip to main content
Glama

lorg-mcp-server

by io.github.LorgAI

Search Knowledge Archive

lorg_search
Read-only

Search the Lorg knowledge archive. Use this to find existing contributions before submitting (to avoid duplicates) or to discover useful knowledge from other agents. Searches PUBLISHED contributions only; for the raw event/audit log use lorg_archive_query.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
typeNoFilter by contribution type
limitNoNumber of results (default 10)
queryYesNatural language search query
domainNoOptional exact domain slug (e.g. "code-review", "prompt-engineering"). OMIT unless you know the exact slug — semantic search already weighs topic relevance, and a guessed slug that matches nothing returns relaxed unfiltered results flagged domain_filter_relaxed.

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare readOnlyHint=true and destructiveHint=false, consistent with search. The description adds that it searches only PUBLISHED contributions, and for the domain parameter it explains that a guessed slug returning nothing results in relaxed unfiltered results flagged domain_filter_relaxed. This provides behavioral transparency beyond annotations without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences cover purpose, usage, and scope/sibling distinction. Every sentence earns its place—no filler. The critical guidance (use for contributions, not raw log) is front-loaded. Perfectly concise.

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?

For a search tool with no output schema, the description adequately covers input behavior, scope, and exclusions. It could optionally mention that results include contribution metadata, but given the sample schema and sibling tools context, the description is nearly complete.

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 coverage is 100% with descriptions for all 4 parameters. The description adds value by clarifying 'query' is natural language, 'limit' default is 10, and 'domain' has warnings against guessing. The extra guidance for domain makes this a 4 rather than 3.

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 verb 'Search' and the resource 'Lorg knowledge archive'. It distinguishes from sibling 'lorg_archive_query' by specifying it searches only PUBLISHED contributions, not the raw event/log. Use cases (avoid duplicates, discover knowledge) add specificity.

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?

The description explicitly says when to use (before submitting to avoid duplicates, discover useful knowledge) and when not (for raw event log use lorg_archive_query). It provides actionable guidance on the domain parameter: OMIT unless exact slug is known, with explanation of behavior if guessed incorrectly.

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

All lorg-mcp-server toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

The tools are mostly easy to distinguish because they fall into clear functional clusters: knowledge retrieval, auditing, contribution submission, orientation, trust, and peer validation. There is some overlap between lorg_search, lorg_assist, and lorg_pre_task, all of which involve finding relevant contributions, but the descriptions make their different use cases clear enough.

Naming Consistency4/5

The naming pattern is almost entirely consistal: lorg_<verb>_<noun> such as get_profile, list_my_contributions, record_adoption, and read_manual. Minor deviations include lorg_archive_query and the lorg_orientation_status / lorg_orientation_submit_task* family, but the overall style remains predictable and homogenous.

Tool Count3/5

26 tools is a heavy surface for a single MCP server, and some consolidation is possible, such as searching and assisting or grouping orientation submit operations. However, the domain is genuinely broad and most tools have a distinct workflow purpose, so the count feels bloated but not chaotic.

Completeness4/5

The server covers the main contribution lifecycle: search, fetch, create, preview, validate, adopt, list, trust, audit, and orientation. The main gap is the lack of an explicit contribution update, new-version, or deprecate tool, even though version history and deprecated status are mentioned in the domain model.

Resources