Skip to main content
Glama

snipara-mcp

PyPI version Python 3.10+ License: MIT CI

snipara-mcp is 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.

Choose the connection

Client capability

Recommended path

Streamable HTTP MCP

Connect directly to https://api.snipara.com/mcp/YOUR_PROJECT_SLUG

Local stdio process only

Use this Python connector with its documented environment

Guided workspace setup

npx create-snipara@latest

Local task tracking without Hosted

Companion

Resolve the project endpoint from your authorized setup. Supply credentials through the client's supported environment or secret mechanism, and check a source citation after connecting. Installing the connector does not select a project, upload documents or install Companion, Orchestrator or Sandbox.

Related MCP server: AgentMemory Offline

What Is Snipara?

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.

Why MCP?

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

The integration should feel small:

uvx snipara-mcp

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

What It Unlocks

Need

Snipara MCP tool group

Ask project docs a source-backed question

snipara_context_query, snipara_get_chunk

Recall durable decisions and learnings

snipara_recall

Review the team Inbox

snipara_inbox_review_queue, snipara_inbox_review_plan, snipara_inbox_review_apply

Persist reusable memory after a task

snipara_remember_if_novel, snipara_end_of_task_commit

Reuse team standards and shared guidance

snipara_shared_context

Inspect structural code relationships

snipara_code_callers, snipara_code_imports, snipara_code_neighbors

Plan risky code changes

snipara_code_symbol_card, snipara_code_impact within plan capacity

Public MCP clients must use the snipara_* names. The rlm_* 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. Set SNIPARA_TOOL_PROFILE=full only for clients that need direct discovery of every specialist compatibility tool; hidden tools remain callable by explicit name and discoverable through snipara_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, and snipara_inbox_review_apply.

Minimum-safe-change review (2.8.30)

The packaged snipara_context_query and snipara_code_impact contracts now accept minimum_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 bounded minimum_change_evidence with named provenance such as runtime, manifest, lockfile, git_diff, or test_runner. Unverified confirmed claims remain visible as asserted; confirmed is reserved for a versioned, fingerprint-matching adapter receipt. The verified adapters are lockfile_manifest for direct installed dependencies and git_diff for a coherent local smallest-safe-diff check. Responses also include non-blocking preservation guards for validation, errors, auth/security, accessibility, public contracts, and tests.

Semantic rule contract (2.8.27)

The generated snipara_code_symbol_card and snipara_code_impact schemas now forward bounded semantic_rules project overrides to the hosted service. Terms are literal strings rather than executable regular expressions.

MCP transport security floor (2.8.26)

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 packaged snipara_code_impact contract now exposes depth (1-6), direction (in, out, or both), and optional edge_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 complete initialize and tools/list before credentials are configured. Every actual tool call still fails closed until authentication and project selection are present. The default tools/list response exposes the same 13-tool core as hosted Snipara, while SNIPARA_TOOL_PROFILE=full retains direct discovery of all specialist compatibility tools. Core tools now include complete selection guidance, behavior annotations, and nested parameter documentation for safer agent use.

Agent-readable tool contracts (2.8.23)

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 and ProjectDecision drafts 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.

Conversational decision review (2.8.21)

Agents can list pending ProjectDecision drafts, 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_commit now accepts an atomic why block with decision, rationale, alternatives, constraints, and observed_outcome. Structured candidates stay pending until human review, and unknown parameters fail closed instead of being silently ignored.

Retrieval outcome controls (2.8.19)

The stdio connector forwards the hosted server's bounded retrieval-outcome controls for context_query and recall: 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.

Architecture

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

Hosted HTTP Or Stdio?

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"
      }
    }
  }
}

Use snipara-mcp when 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"
      }
    }
  }
}

Decision rule:

  • HTTP MCP first for modern clients

  • snipara-mcp for stdio-only clients or local compatibility

  • create-snipara when you want guided setup across clients and templates

Install

No local install:

uvx snipara-mcp

Python package:

pip install snipara-mcp

With RLM Runtime helper integration:

pip install "snipara-mcp[rlm]"

Quickstart

Sign in through the browser:

pip install snipara-mcp
snipara login

Initialize a project:

snipara init

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

Useful options:

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

Claude Code

claude mcp add snipara uvx snipara-mcp

Then export credentials in your shell:

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

Cursor

Add to ~/.cursor/mcp.json:

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

Environment

Variable

Required

Description

SNIPARA_API_KEY

Yes, unless using snipara login

Snipara API key

SNIPARA_PROJECT_ID

Yes, unless using SNIPARA_PROJECT_SLUG

Project identifier

SNIPARA_PROJECT_SLUG

Yes, unless using SNIPARA_PROJECT_ID

Project slug

SNIPARA_API_URL

No

Defaults to https://api.snipara.com

SNIPARA_TOOL_PROFILE

No

core by default; full exposes specialist tool schemas

OAuth tokens created by snipara login are 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.

What You Get

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 with SNIPARA_TOOL_PROFILE=full.

Common tool groups:

  • 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

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

CLI Commands

Command

Description

snipara login

Browser login and token setup

snipara init

Initialize Snipara in the current project

snipara logout

Clear stored tokens

snipara status

Show auth and project status

snipara-mcp

Run the MCP stdio server

Legacy aliases such as snipara-init, snipara-mcp-login, snipara-mcp-logout, and snipara-mcp-status are still supported.

Relationship To Other Repos

Repo

Role

alopez3006/snipara-mcp

Current generated public connector mirror

Snipara/snipara-companion

Local workflow, impact, verification, and handoff CLI

Snipara/snipara-memory

Open memory primitives and schema

snipara-mcp is 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.

Development

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.

License

MIT. See LICENSE.

Conceptual research with bounded query plans (2.8.39)

snipara_context_query accepts up to four optional retrieval_queries authored by the agent. Describe concrete mechanisms, capabilities, constraints and counterevidence in the source language. Keep the original question in query and preserve named entities. The hosted server combines ranked sources within one strict max_tokens budget, including Answer Packs and chunk references. Facets are hypotheses, not facts; unsupported claims remain unknown. The server does not run its own LLM to generate the plan. Existing calls remain compatible when the optional field is omitted.

3.0 context-query migration

The primary text block of a default stdio snipara_context_query response is compact JSON. Session context may appear in a separate text block. Retrieved sources, citations and caveats are preserved, with Answer Packs and automatic query decomposition disabled by default. Consumers that parsed the previous Markdown response should request include_metadata=true to use the full response format. That full mode retains the previous defaults; set include_answer_pack=false and auto_decompose=false explicitly if you only need source retrieval.

In compact mode, request include_answer_pack=true or auto_decompose=true only when needed. max_tokens bounds the selected retrieval content, not the complete serialized MCP response. Smaller responses do not establish better answer accuracy or lower end-to-end latency.

3.0 memory context contract

Recall accepts up to four retrieval_queries for source-language translations or question facets. Owner scope, minimum relevance and final result limits still apply.

Recall defaults to memory_view="current": active, currently effective candidates; source observations are checked against their accessible source on this read. Choose retained history explicitly when asking about an earlier state:

snipara_recall(query="workflow status", memory_view="current")
snipara_recall(
    query="workflow status",
    memory_view="history",
    as_of="2026-10-25T10:00:00Z",
)

The equivalent CLI options are snipara recall "workflow status" --memory-view history --as-of 2026-10-25T10:00:00Z, or snipara-companion recall --query "workflow status" --memory-view history --as-of 2026-10-25T10:00:00Z --json. Query prose alone does not select a historical view. as_of requires history and a past timestamp with a timezone. Current access, owner scope and retention/TTL still apply: history never restores expired/deleted content or reconstructs unavailable mutable source versions. Stored source-observation receipts can support an earlier recorded assertion; their integrity hashes do not cryptographically authenticate origin, and older records may predate the reserved-writer guard. Generic evidence attachment cannot write the reserved observation descriptor/receipt namespace. Historical receipts grant no current authority, current handoff evidence or check reuse. Historical authority is marked ineligible for current use, without declaring the old evidence false or changing stored lifecycle/review state. Conflicting explicit checkpoints retain an unresolved conflict rather than a winner selected by recency.

Default calls remain compatible with older servers. For explicit history/as-of, these clients refuse a missing or mismatched temporal_context confirmation rather than silently accepting a current result. Candidate selection combines the bounded recent pool with bounded literal recovery; neither a successful source check nor an empty result establishes that no older relevant memory exists.

snipara_resume_context(mode="context") returns agent-resume-context-v2 with freshly verified project observation references. Pass memory_ids cited by the producer; missing, inaccessible, withdrawn or over-budget evidence yields an abstention and an automatic recovery action. Calls without mode or source/proposal fields retain the historical continuity contract, including Companion branch/files/token-budget arguments. mode="continuity" explicitly selects it. Memory IDs imply context mode, while explicit continuity rejects source/proposal fields. Never treat continuity history as current source or execution proof. The 3.0.0 contract also accepts proposed_actions on resume. Submit the model's plan before consuming it; the hosted validator automatically blocks check reuse and proposes evidence recovery without execution authorization. Memory recall now uses optional facets only for weak or ambiguous initial rankings; counters remain in telemetry. This does not intercept external tools invoked outside the Snipara contract. Context-refresh proposals also expose whether their target exactly resolves to an already-loaded verified memory/source locator. Unresolved free text stays advisory; resolution performs no refresh and grants no execution authority.

The unpublished compact validate_actions beta is withdrawn from the advertised contract after reader precision regressions. Old beta calls automatically fall back to source-verified context and return resumeContext; this fallback provides no zero-read/token-saving guarantee. Use mode="context" for current facts and proposal validation. Responses expose current allowed citation IDs; optional proposed_citations checks membership, never the truth of the answer's claims. The two behaviors are continuity and context; the schema retains validate_actions as a deprecated alias for context. The client remains unpublished.

Available Tools

12 tools
snipara_askA
Read-onlyIdempotent

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.

Inputs: query (required), correlation_context.

snipara_context_queryA
Read-onlyIdempotent

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. 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.

Inputs: query (required), task, max_tokens, search_mode, +9 more.

snipara_end_of_task_commitA

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; 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.

Inputs: why, task, dry_run, outcome, +8 more.

snipara_get_chunkA
Read-onlyIdempotent

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.

Inputs: chunk_id (required), correlation_context.

snipara_inbox_review_applyA
Destructive

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.

Inputs: reason (required), actions (required), review_plan_id (required).

snipara_inbox_review_planA
Read-onlyIdempotent

Validate evidence-backed recommendations for team Inbox memory candidates and ProjectDecision drafts without changing authority. This read-only ADMIN operation creates a snapshot-bound review_plan_id; approve/reject items enter the snapshot while needs_human items remain pending. Use snipara_inbox_review_queue first and never call apply without explicit human authorization. Returns the immutable plan, exclusions, and validation findings.

Inputs: recommendations (required).

snipara_inbox_review_queueA
Read-onlyIdempotent

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.

Inputs: limit.

snipara_readA
Read-onlyIdempotent

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.

Inputs: end_line, file_path, start_line.

snipara_recallA
Read-onlyIdempotent

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.

Inputs: query (required), task, type, limit, +9 more.

snipara_remember_if_novelA
Idempotent

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, while auto_safe reconciliation may supersede high-confidence same-owner matches without deleting them. 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.

Inputs: text (required), type, scope, source, +10 more.

snipara_statsA
Read-onlyIdempotent

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.

Inputs: max_files, include_files, include_index_health.

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A4.6/5.0

    Scored across 12 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: ask, context query, search, read line range, get chunk, recall memory, remember if novel, end-of-task commit, inbox review queue/plan/apply, and stats. No overlapping functionality.

    Naming Consistency5/5

    All tools follow a consistent 'snipara_' prefix with snake_case descriptive names (e.g., snipara_context_query, snipara_end_of_task_commit). No mixing of conventions or abbreviations.

    Tool Count5/5

    12 tools is well-scoped for a documentation and memory management server. It covers viewing, searching, querying, memory operations, inbox review workflow, and statistics without being overwhelming or sparse.

    Completeness4/5

    The tool surface covers core retrieval, memory storage, and inbox review. Minor gaps include the lack of an explicit update or delete for memories, but the server appears focused on append and recall. Overall coverage is strong.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Provides persistent, searchable memory for AI agents across any MCP-compatible client, storing project context, user preferences, and session learnings locally in SQLite with tools to save, retrieve, search, and manage them.
      12
      9 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables MCP-compatible AI agents to connect to SoluCortex projects, recall relevant technical decisions, conventions, risks, and architecture before working, and record new memories afterward.
      4
      MIT