MCP App Store
by KeenEthics
Snipara icon

Snipara MCP Server for ChatGPT

By Starbox Group Gmbh

Overview

Desktop plugin for sourced Snipara project context and reviewed memory, local Companion checkpoints and explicit Orchestrator coordination. Sign in to one authorized project through native OAuth. Companion and Orchestrator are optional, independently disableable local programs installed only on request at pinned versions. They require an explicitly configured project and separate runtime authentication. No lifecycle hook runs at session start. Tasks, memory writes and runtime credential sharing require authorization. A Snipara account and authorized project access are required.

How to connect

  1. ChatGPT: Open the Snipara listing in the ChatGPT app directory and choose Connect. ChatGPT listing Snipara exposes 13 tools here.

Tools

snipara_ask

ChatGPT
Answer one simple question from indexed project documentation with server-side synthesis. This is a read-only VIEWER operation and changes no project state. Use snipara_context_query when citations, answer packs, retrieval controls, or source sections matter; use snipara_search for an exact regex. Returns a concise answer or a bounded no-match/error result.

snipara_context_query

ChatGPT
Query project documents, parsed business files, and shared context. Use this first for source truth and narrative documentation. Returns a source-grounded answer_pack plus retrieval_diagnostics and ranked sections within token budget. For conceptual, cross-language or multi-part questions, supply 2-4 retrieval_queries with concrete mechanisms, capabilities, constraints and counterevidence in the source language. If a broad query times out, retry once with a narrow 3-8 term query, max_tokens 800-1500, search_mode='keyword', return_references=true, auto_decompose=false, and include_all_tiers=false. For exact text use snipara_search; for structural code context use snipara_code_neighbors, snipara_code_callers, or snipara_code_imports.

snipara_end_of_task_commit

ChatGPT
Persist a bounded end-of-task summary, optional structured Why Capture, and selected durable outcomes so another agent can resume the work. This EDITOR operation writes memory and workflow state and is non-idempotent. With auto_safe reconciliation it may also mark older same-owner memories as superseded, changing which records are current while retaining their history. dry_run validates without writing. Use snipara_remember_if_novel for one reusable memory and document upload tools for source material. Unknown fields fail closed. Returns created or skipped records, review candidates, handoff metadata, and validation warnings.

snipara_get_chunk

ChatGPT
Fetch one complete indexed source chunk by the stable chunk ID returned from a reference-based context query. This is a read-only VIEWER operation and changes no project state. Use snipara_context_query first to discover relevant references; use snipara_read for an exact document line range instead. Returns the chunk text, source identity, position metadata, and a bounded not-found/error result.

snipara_help

ChatGPT
Read Snipara tool documentation and discovery metadata. This read-only operation returns tool names, descriptions and schemas; it never invokes another tool, runs a command, or changes project state. It is not an execution proxy. Use query for recommendations, tool for one contract, tier for a category, or list_all for the catalog. A documented tool is callable only when the client separately exposes its own MCP contract and the caller has permission. Returns selection guidance, examples, access requirements, exposure metadata, and related tool names.

snipara_inbox_review_apply

ChatGPT
Atomically apply the exact memory-candidate and decision-draft actions from a prior team Inbox review plan. This destructive ADMIN operation requires explicit user authorization plus a real human team-admin identity, records authority audits, and fails closed if any item or snapshot changed. It is not idempotent and must follow snipara_inbox_review_plan. Returns per-item outcomes and the atomic apply receipt.

snipara_inbox_review_plan

ChatGPT
Preview evidence-backed recommendations for team Inbox memory candidates and ProjectDecision drafts. This read-only ADMIN operation reads pending items and computes a deterministic snapshot-hash review_plan_id in its response. It does not save a plan, approve or reject items, or change authority or review state. needs_human items remain outside the proposed apply snapshot. Use snipara_inbox_review_queue first; only the separate snipara_inbox_review_apply tool can apply changes after explicit human authorization. Returns the computed preview, exclusions, and validation findings.

snipara_inbox_review_queue

ChatGPT
List human-reviewable memory candidates and ProjectDecision drafts from the current user's team Dashboard Inbox. This is a read-only ADMIN operation and changes no authority or review state; credential-like material is redacted. Use snipara_inbox_review_plan to validate recommendations before any authorized mutation. Returns stable item IDs, project ownership, evidence, and current review status.

snipara_read

ChatGPT
Read an exact line range from indexed project documentation. This is a read-only VIEWER operation and changes no project state. Use it after snipara_search or snipara_context_query when exact wording matters; use snipara_get_chunk instead when you already have a cited chunk ID. Returns the resolved range and text, or a validation/not-found error.

snipara_recall

ChatGPT
Semantically recall durable Memory V2 decisions, learnings, preferences, and session carryover within the requested owner boundary. This is a read-only VIEWER operation and changes no memory authority. Use snipara_context_query for source documents and snipara_memories for lifecycle inventory. Returns ranked active memories, optional inactive warnings, authority metadata, and bounded retrieval diagnostics.

snipara_remember_if_novel

ChatGPT
Store one durable Memory V2 record only when it is sufficiently different from existing reviewed memory. This EDITOR operation may write project, team, user, or agent state; duplicate calls normally skip the write. Explicit corrections and auto_safe reconciliation may mark older matching memories as superseded, changing which records are current. Superseded records are retained rather than deleted. Use snipara_end_of_task_commit for multi-outcome workflow capture and context tools for source documents. Returns whether storage occurred, duplicate evidence, the memory ID, and reconciliation actions.

snipara_stats

ChatGPT
Read compact project documentation and retrieval statistics without changing project state. File samples and database-backed index health are opt-in to keep the response small. Use snipara_index_health for operational diagnosis rather than this overview. Returns counts, token/index summaries, and only the optional sections requested.

Capabilities

Writes

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/snipara"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/snipara)