Skip to main content
Glama
Living Stack MCP — Retired Beta Listing

Living Stack MCP — Retired Beta Listing

Living Stack MCP

Living Stack MCP gives MCP-capable AI agents a bounded control-and-proof plane: scoped continuity, action authorization, budget reservations, typed outcome evidence, claim gates, durable checkpoints, and cryptographically signed trace exports. It does not replace the model or execute the customer's actions.

Try the complete Community edition free:

npx -y github:equinoxaifinance-rgb/living-stack-mcp#v0.3.4-beta.1 --self-test

That sixty-second local proof sends nothing. If one private workspace needs to coordinate up to five installations, Team Local is $19 once.

The repository is also a portable Agent Plugins 1.0 bundle: compatible clients can install the MCP server and its operating skill together from the same pinned release.

What ships in 0.3 public beta

  • 15 bounded MCP tools and three guided lifecycle prompts over local stdio.

  • Per-session state with append-only SHA-256-linked evidence ledgers.

  • Server-owned risk policy; external and destructive actions are denied by default.

  • Cost reservation and reconciliation against a session ceiling.

  • Credential-shaped value redaction before persistence or protocol output.

  • Scope-, state-, expiry-, and lineage-bound recovery checkpoints.

  • Ed25519-signed trace exports tied to one local installation.

  • An explicit-consent, minimal signed adoption receipt; no session or task payload is accepted.

  • Optional offline entitlement grants; billing secrets never enter the MCP.

Related MCP server: CodexPro Runtime

Install

Requires Node.js 22 or later.

MCP bundle

Download the SHA-256-release-bound Living Stack MCP bundle and import it into an MCPB-compatible client. Verify downloaded bytes against the SHA256SUMS.txt asset attached to that exact GitHub release.

The same bundle and hash are active in the official MCP Registry. The indexed tool surface is also live on Glama and Smithery.

The live remote commerce MCP is separately available through the official MCP Registry and its Smithery gateway.

Install in VS Code, add it to Cursor, or follow the exact-version Codex, Claude Code, VS Code, Cursor, and desktop client guide.

Command line

npx -y github:equinoxaifinance-rgb/living-stack-mcp#v0.3.4-beta.1

Prove the package locally before configuring a host:

npx -y github:equinoxaifinance-rgb/living-stack-mcp#v0.3.4-beta.1 --self-test

That command exercises a new bounded session, authorization, typed outcome, claim gate, checkpoint round trip, signed trace, and clean session close. It does not contact Living Stack. To send one minimal signed first-run receipt, the user must deliberately add --report-first-run --host=<host>; the exact fields are listed in the Privacy section below.

Or install globally:

npm install -g github:equinoxaifinance-rgb/living-stack-mcp#v0.3.4-beta.1
living-stack-mcp

Minimal MCP configuration:

{
  "mcpServers": {
    "living-stack": {
      "command": "npx",
      "args": ["-y", "github:equinoxaifinance-rgb/living-stack-mcp#v0.3.4-beta.1"]
    }
  }
}

State defaults to ~/.living-stack-mcp/state. Set LIVING_STACK_STATE_DIR to a dedicated directory. Set LIVING_STACK_ALLOWED_ROOTS to explicit roots if release-manifest verification is needed.

First agent run

Ask the connected agent to use the native livingstack.prove_task prompt, or copy the concise workflow in QUICKSTART.md. The guided path freezes scope and budget before action, authorizes an exact target, records typed evidence references afterward, retains explicit outcome IDs, and blocks unsupported completion language unless the identical subject and selected fresh outcomes support it—without taking over the host's tools.

Lifecycle

  1. livingstack.session_start freezes scope, goal, retention, and budget.

  2. livingstack.context_put stores provenance-labeled context.

  3. livingstack.authorize_action checks risk and reserves cost.

  4. The MCP host performs the action with its own tools and permissions.

  5. livingstack.record_outcome consumes authorization and records evidence.

  6. livingstack.check_claim tests a claim only against explicit fresh successful outcome_ids bound to the exact authorization target supplied again as subject; unrelated session evidence cannot satisfy it.

  7. Checkpoint tools preserve and verify bounded recoverable state.

  8. Trace tools expose redacted reports and workspace-signed exports.

Security boundaries

Living Stack MCP has no arbitrary shell, browser, database, deployment, or publication tools and no arbitrary HTTP capability. Its single publisher network action is a fixed-schema, fixed-origin adoption receipt that remains inert unless the user explicitly sets consent. It does not inspect personal Codex or Claude state. A workspace signature proves that an export came from one local installation; it does not by itself prove publisher or user identity. The host remains the authority and executor.

The complete Community edition is local-first and free. Team Local is available separately for $19 once; it coordinates one private workspace and up to five registered installations without changing the model or uploading Community session state. Exact scope, purchase paths, and boundaries are documented in COMMERCIAL.md.

See PRODUCT.md, SECURITY.md, and CHANGELOG.md. Installation paths are collected in CLIENTS.md.

Development

npm ci
npm test
npm run verify

License: Apache-2.0.

Brand assets and their meaning are documented in BRAND.md.

Privacy Policy

Living Stack Community runs locally and never sends session state, context, ledgers, checkpoints, private signing keys, or agent payloads to Living Stack. An optional first-run receipt is sent only after explicit consent and contains the package version, milestone, coarse host category, installation public-key hash, timestamp, and signature. The endpoint rejects arbitrary metadata. The complete policy covers collection, local use and storage, third-party sharing, retention, and contact information at living-stack-mcp.pages.dev/privacy.html.

Available Tools

14 tools
livingstack.authorize_actionAuthorize a Bounded Agent ActionAInspect

Evaluate an intended action against server-owned risk policy and the session budget. The default policy denies external and destructive risks, and this server never executes the action itself.

Inputs: action_id (required), session_id (required), action_type (required), risk, +2 more. Returns: object

livingstack.check_claimBind a Claim to Current EvidenceCInspect

Determine whether a completion, working, integrity, or deployment claim has fresh successful typed evidence in the verified session ledger.

Inputs: claim_text (required), session_id (required), claim_type, max_age_seconds, +1 more. Returns: object

livingstack.checkpoint_loadRestore a Durable CheckpointBInspect

Load a checkpoint only after session, scope, state hash, expiry, ledger integrity, and lineage checks pass.

Inputs: session_id (required), checkpoint_id (required). Returns: object

livingstack.checkpoint_saveSave a Durable CheckpointBInspect

Redact and persist a bounded state object bound to the session scope and current ledger lineage.

Inputs: label (required), state (required), session_id (required), retention_hours. Returns: object

livingstack.context_putStore Scoped ContextAInspect

Add redacted, provenance-labeled context to the current session. Stored context remains historical until independently reverified.

Inputs: text (required), source (required), session_id (required), tags. Returns: object

livingstack.record_outcomeRecord an Authorized OutcomeAInspect

Consume one prior authorization, reconcile reserved cost, and append a tamper-evident outcome with typed evidence references.

Inputs: session_id (required), classification (required), authorization_id (required), summary, +3 more. Returns: object

livingstack.retrieve_contextRetrieve Scoped ContextA
Read-onlyIdempotent
Inspect

Search only the current session context using deterministic lexical retrieval and return provenance plus receipt hashes.

Inputs: query (required), session_id (required), limit. Returns: object

livingstack.session_closeClose a Runtime SessionAInspect

Mark a session closed while preserving its tamper-evident evidence history.

Inputs: session_id (required), reason. Returns: object

livingstack.session_startStart a Scoped Runtime SessionAInspect

Create an isolated capability session with an immutable scope, goal, retention period, and hard between-action budget ceiling.

Inputs: goal (required), scope (required), retention_hours, budget_limit_usd. Returns: object

livingstack.session_statusInspect a Runtime SessionA
Read-onlyIdempotent
Inspect

Read the current scope hash, lifecycle status, budget, pending authorization count, and ledger integrity for one session.

Inputs: session_id (required). Returns: object

livingstack.statusLiving Stack Capability StatusA
Read-onlyIdempotent
Inspect

Describe this standalone Living Stack MCP server, its enforced boundaries, configured risk policy, and available capability classes. This does not inspect a customer session.

Inputs: no named parameters. Returns: object

livingstack.trace_exportExport Redacted OTLP JSON TracesA
Read-onlyIdempotent
Inspect

Convert the verified lifecycle ledger into metadata-only OTLP/JSON trace data and sign the exact export with the local workspace Ed25519 identity. Raw context, goals, targets, summaries, and checkpoint state are excluded.

Inputs: session_id (required). Returns: object

livingstack.trace_reportGenerate a Redacted Trace ReportA
Read-onlyIdempotent
Inspect

Verify the event chain and return aggregate event, outcome, budget, and lifecycle data without raw private payloads.

Inputs: session_id (required). Returns: object

livingstack.verify_releaseVerify Release Bytes Against a ManifestA
Read-onlyIdempotent
Inspect

Freshly hash each declared file from a JSON manifest under a host-configured allowed root. Paths outside configured roots remain unresolved.

Inputs: manifest_path (required). Returns: object

Tool Schema Changelog

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

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 14 tools

    Disambiguation5/5

    Each tool targets a distinct resource or lifecycle step: session status vs server status, context retrieval vs checkpoint loading, and trace report vs trace export are all clearly separated by their descriptions. No two tools appear to perform the same operation.

    Naming Consistency3/5

    All tools share the livingstack prefix and snake_case, but the object/verb order is inconsistent: session_start, context_put, and checkpoint_save are noun-verb while retrieve_context, authorize_action, and check_claim are verb-noun. Status, session_status, trace_report, and trace_export are noun-like, so no single naming pattern dominates.

    Tool Count5/5

    Fourteen tools is within the ideal 3-15 range and each tool maps to a distinct capability class such as session lifecycle, context management, authorization, checkpointing, tracing, and release verification. The count feels deliberately scoped rather than padded.

    Completeness4/5

    The core session, context, authorization, outcome, checkpoint, trace, and release verification lifecycle is well covered. Minor gaps exist: context_put mentions independent reverification but no explicit tool exposes that operation, and there is no session-listing or session-deletion tool beyond close.

    Maintenance

    ActivityNo data
    ResponsivenessSyncing

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      A local, evidence-driven MCP runtime and control plane for open-source maintainers that provides workspace-bounded tools including controlled file operations, command execution, validation primitives, durable execution records, and human review workflows via stdio and Streamable HTTP transports.
      33
      MIT