Snipara

snipara-mcpis the lightweight stdio MCP connector for the Snipara Project Brain.

Snipara is the Project Brain for AI coding agents.

Use it when an MCP client needs a local stdio process that talks to Snipara's hosted Project Intelligence APIs. Snipara gives Claude Code, Cursor, Codex, and other MCP clients the decisions, active work, code impact, proof, and handoffs they need before they edit. If your client supports streamable HTTP MCP directly, prefer the hosted endpoint and skip the local process.

Snipara is the shared Project Intelligence layer for AI-assisted software work.

It gives Claude Code, Cursor, Codex, OpenAI Agents, and other MCP-compatible clients project context that survives sessions, users, tools, and model switches.

Your agent still uses its own LLM. Snipara gives it the right project context: source-backed docs, reviewed memory, shared guidance, workflow continuity, and code graph structure. In category terms, it is an AI coding agent context, memory, and continuity platform.

MCP is becoming a standard adapter layer for agent tools.snipara-mcpmakes Snipara available through that layer without forcing developers into a specific IDE, model, or orchestration framework.

The impact is larger: agents can retrieve durable project context instead of starting cold every session.

Public MCP clients must use thesnipara_names. Therlm_compatibility aliases were removed from the distributed contract on 2026-08-16 and remain only as internal handler identifiers. This contract cleanup is staged for the next package release; clients using legacy names must migrate before upgrading.

The stdio server advertises the same compact default agent contract as the hosted MCP endpoint. SetSNIPARA_TOOL_PROFILE=fullonly for clients that need direct discovery of every specialist compatibility tool; hidden tools remain callable by explicit name and discoverable throughsnipara_help.

The default discovery surface contains 13 coherent tools:snipara_context_query,snipara_ask,snipara_search,snipara_read,snipara_stats,snipara_help,snipara_get_chunk,snipara_recall,snipara_remember_if_novel,snipara_end_of_task_commit,snipara_inbox_review_queue,snipara_inbox_review_plan, andsnipara_inbox_review_apply.

The packagedsnipara_context_queryandsnipara_code_impactcontracts now acceptminimum_change_mode="review". When enabled, answer packs and impact responses carry a non-blocking, evidence-first receipt covering existing capabilities, stdlib/native options, installed dependencies, the smallest safe diff, and validation-surface preservation. The policy is advisory and remains opt-in until project evidence calibrates stronger enforcement.

Callers may provide boundedminimum_change_evidencewith named provenance such asruntime,manifest,lockfile,git_diff, ortest_runner. Unverifiedconfirmedclaims remain visible asasserted;confirmedis reserved for a versioned, fingerprint-matching adapter receipt. The verified adapters arelockfile_manifestfor direct installed dependencies andgit_difffor a coherent local smallest-safe-diff check. Responses also include non-blocking preservation guards for validation, errors, auth/security, accessibility, public contracts, and tests.

The generatedsnipara_code_symbol_cardandsnipara_code_impactschemas now forward boundedsemantic_rulesproject overrides to the hosted service. Terms are literal strings rather than executable regular expressions.

The connector now requires MCP Python SDK 1.28.1 or newer. This incorporates the upstream fixes for authenticated-principal session isolation, experimental task ownership, and WebSocket Host/Origin validation.

Configurable code-impact traversal (2.8.25)

The packagedsnipara_code_impactcontract now exposesdepth(1-6),direction(in,out, orboth), and optionaledge_kinds. This keeps the connector contract aligned with hosted impact chains and Companion's hybrid local/hosted traversal controls.

Credential-free discovery and compact contract (2.8.24)

MCP clients and directory inspectors can now completeinitializeandtools/listbefore credentials are configured. Every actual tool call still fails closed until authentication and project selection are present. The defaulttools/listresponse exposes the same 13-tool core as hosted Snipara, whileSNIPARA_TOOL_PROFILE=fullretains direct discovery of all specialist compatibility tools. Core tools now include complete selection guidance, behavior annotations, and nested parameter documentation for safer agent use.

The connector now preserves detailed tool descriptions and MCP behavior annotations from the hosted source of truth. Summary, coordination, state, memory, and code graph tools explain their prerequisites, access rules, side effects, idempotence, alternatives, parameters, outputs, and common failure modes so agents can choose them safely. Native output schemas remain deferred until the transport and structured result format upgrade together.

Unified conversational Inbox review (2.8.22)

Human team admins can list the same memory candidates andProjectDecisiondrafts shown by the multi-project Dashboard Inbox, create evidence-backed approve/reject/needs-human recommendations, and atomically apply an explicitly authorized snapshot. The service revalidates the human team-admin identity, project ownership, current candidate states, and immutable item snapshots before recording authority audits. Real credentials remain addressable for rejection but are redacted from MCP output. The earlier ProjectDecision-only tools remain available as specialist compatibility tools.

Agents can list pendingProjectDecisiondrafts, propose evidence-backed approve/reject/needs-human recommendations, and apply an explicitly authorized snapshot-bound plan. Apply requires a human project admin and fails closed if a draft changed after planning; there is no live wildcard approval.

Structured Why Capture task commits (2.8.20)

snipara_end_of_task_commitnow accepts an atomicwhyblock withdecision,rationale,alternatives,constraints, andobserved_outcome. Structured candidates stay pending until human review, and unknown parameters fail closed instead of being silently ignored.

The stdio connector forwards the hosted server's bounded retrieval-outcome controls forcontext_queryandrecall: optional task correlation, shadow or enabled rerank requests, and the strict context attribution window. The hosted server remains authoritative, so a client request can lower or disable the configured mode but cannot escalate it.

flowchart LR Agents["Claude Code, Cursor, Codex, ChatGPT, OpenAI agents"] --> Stdio["snipara-mcp stdio process"] Stdio --> Hosted["Hosted Snipara MCP API"] Hosted --> Context["Context engine"] Hosted --> Memory["Project memory"] Hosted --> Graph["Code graph"] Context --> AgentLLM["Agent's own LLM"] Memory --> AgentLLM Graph --> AgentLLM

Use the hosted HTTP endpoint when your MCP client supports streamable HTTP:

{ "mcpServers": { "snipara": { "type": "http", "url": "https://api.snipara.com/mcp/your-project-id-or-slug", "headers": { "Authorization": "Bearer snp-your-key" } } } }

Usesnipara-mcpwhen your client expects a local stdio command:

{ "mcpServers": { "snipara": { "command": "uvx", "args": ["snipara-mcp"], "env": { "SNIPARA_API_KEY": "snp-your-key", "SNIPARA_PROJECT_ID": "your-project-id-or-slug" } } } }

- HTTP MCP first for modern clients
- snipara-mcpfor stdio-only clients or local compatibility
- create-sniparawhen you want guided setup across clients and templates

pip install "snipara-mcp[rlm]"

The initializer detects common project files, writes MCP configuration, and can upload local project docs when you are authenticated.

snipara init --slug my-project snipara init --dry-run snipara init --no-upload snipara init --skip-test

export SNIPARA_API_KEY="snp-your-key" export SNIPARA_PROJECT_ID="your-project-id-or-slug"

{ "mcpServers": { "snipara": { "command": "uvx", "args": ["snipara-mcp"], "env": { "SNIPARA_API_KEY": "snp-your-key", "SNIPARA_PROJECT_ID": "your-project-id-or-slug" } } } }

OAuth tokens created bysnipara loginare stored in~/.snipara/tokens.json. If a project id or slug is set, the connector selects the matching token and does not silently fall back to another project.

The connector exposes the same compact default MCP contract as the hosted backend. The packaged full compatibility surface is generated from the server source of truth and is available withSNIPARA_TOOL_PROFILE=full.

- retrieval:snipara_context_query,snipara_search,snipara_get_chunk,snipara_load_document
- durable memory:snipara_recall,snipara_remember,snipara_memory_compact
- owner-aware bootstrap:snipara_session_memories,snipara_owner_profile_get,snipara_owner_profile_update
- shared context:snipara_shared_context, collection and template tools
- document upload:snipara_upload_document,snipara_sync_documents
- project setup: client, project, and business-context workspace tools
- operations:snipara_settings,snipara_index_health,snipara_reindex
- code graph:snipara_code_*tools when code indexes are available
- coordination: swarm, hierarchical task, and state tools when enabled

Tool availability can vary by plan, hosted deployment, and project index state.

Legacy aliases such assnipara-init,snipara-mcp-login,snipara-mcp-logout, andsnipara-mcp-statusare still supported.

snipara-mcpis intentionally thin. It should be easy to install, easy to audit, and boring to operate. The heavy lifting stays in Snipara's hosted context and memory engine.

pip install -e ".[dev]" pytest ruff check .

The source of truth for the generated tool contract lives in the Snipara server. When backend tools change, regenerate the packaged contract before publishing this package.

Local-first agent memory: a plain-Markdown Obsidian vault is the source of truth, with a rebuildable DuckDB index for hybrid BM25 + vector + graph recall.

Persistent memory and semantic search for AI coding assistants across sessions

Give your agent a memory: shared, cited, tenant-isolated knowledge-graph memory for any MCP host. Grounded answers from a local-first June endpoint — abstains rather than guesses.

Decentralized persistent memory for AI agents — encrypted vault storage built on Walrus and Sui.

Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.

Your portable AI memory vault — memories, skills & configs, shared across every AI tool.

Local Work Model for AI agents that learns from real outcomes.

Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.

Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.

Turns your task manager into agent memory: hybrid (RRF) retrieval over TickTick or an Obsidian vault via an adapter contract. MCP server + CLI, no vector DB to maintain.