Skip to main content
Glama

Liminal

Server Details

Augment your work with Liminal. Stop repeating yourself and build on what’s already solved.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
jaybro2042-alt/liminality-mcp
GitHub Stars
0
Server Listing
Liminal
ChatGPT
–
Claude
–

TDQS

B3.3/5.0

Scored across 9 tools

Disambiguation3/5

Search, research, solve, and focus all relate to obtaining answers, and code_mode vs get_capabilities both handle tool discovery, creating some overlap. However, descriptions clarify the distinct intents (saved answers vs web research vs complex decisions vs passage extraction), reducing confusion.

Naming Consistency4/5

Names are consistently lowercase and use underscores for multi-word terms, but the grammatical form varies (verbs like fetch, focus, read; noun handoff; compound code_mode), which slightly breaks the verb_noun predictability.

Tool Count5/5

Nine tools fit well within the 3-15 range, covering discovery, research, retrieval, and session management without redundancy.

Completeness4/5

Core workflows (search saved answers, web research, passage extraction, fetch full text, read results, session handoff) are covered. Minor gaps like update/delete for saved answers or richer session management are workable.

Available Tools

9 tools
code_modeBInspect

Discover tools for the Liminal Python Code Mode client. search(query) returns public method names; describe(tool) returns its schema. Code executes in the consuming client's isolated runtime; every method uses ordinary authenticated MCP.

Inputs: context (required), tool, query, action, +1 more.

fetchA
Read-onlyIdempotent
Inspect

Full saved answer text by exact search id; caller-owned only.

Inputs: id (required), context (required), llm_model. Returns: id, url, text, title, +1 more

focusAInspect

Pass a URL or long text plus task; returns the answer-bearing passages verbatim. Use instead of opening anything over 8,000 chars. More args: get_capabilities(tool=...).

Inputs: task (required), text (required), context (required), llm_model.

get_capabilitiesBInspect

Every Liminal tool; tool= returns its full argument schema.

Inputs: context (required), tool, llm_model.

handoffBInspect

Save or continue work across sessions. create: task, session_state, evidence, subject. resume: subject or handoff_id. list. More args: get_capabilities(tool=...).

Inputs: action (required), context (required), task, subject, +4 more.

readCInspect

Your saved results and sources. kind: work|results|sources; query filters.

Inputs: context (required), kind, query, llm_model.

researchCInspect

Web research question answered with fetched, cited findings. More args: get_capabilities(tool=...).

Inputs: context (required), question (required), llm_model.

solveBInspect

Frame and answer a non-trivial decision or multi-step request in one call; skip simple lookups. More args: get_capabilities(tool=...).

Inputs: question (required), context, task_id, llm_model, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Supercharges AI coding agents with semantic code intelligence, providing pre-built knowledge graphs for surgical context, faster answers, and fewer tool calls.
      MIT
    • F
      license
      A
      quality
      C
      maintenance
      Semantic memory for AI builders: capture the tacit engineering know-how that never reaches your docs, recall it the moment it applies. Built in Rust on Postgres and pgvector.
      10
      10
      -
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.