
Mcp State Sidecar
io.github.askadvaithPublished by GitHub account askadvaithv0.1.0Updated Oct 24, 2026
MCP State Sidecar: durable state persistence for multi-agent AI workflows
Overview
A local MCP server that stores durable workflow state for multi-agent systems: key-value data, workflow claims, leases, sessions and audit history.
- What you can do
- Read, write, list and delete JSON key-value entries with optional TTL.
- Create, discover, claim, checkpoint, resume and list workflows with run IDs.
- Acquire, renew and release exclusive leases for concurrency control.
- Save and restore session snapshots, and read recent state-transition history.
- Check sidecar health and backend metrics, or wipe all stored data.
- When to use it
- Useful when several agents or processes must share state that survives crashes, horizontal scaling or framework changes, and you want coordination through MCP tools instead of in-process memory or out-of-band messaging.
- Requirements
- Runs locally as a Python package installed with pip; the Redis backend needs the extra redis install and a reachable Redis URL. Configured through environment variables such as STATE_BACKEND, DB_PATH, REDIS_URL, SIDECAR_HOST and SIDECAR_PORT. Stdio mode for local subprocesses, or an HTTP SSE mode that binds to 0.0.0.0 on port 8000 by default.
Installation
In SourceWeft
- Open Mcp State Sidecar in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
MCP State Sidecar Server
[PyPI version] [PyPI - Python Version] [License: MIT] [MCP Registry]
An MCP-native state sidecar that externalises workflow state for distributed agent deployments.
Quite a simple idea really; instead of storing state inside agents (which breaks when processes crash, scale horizontally, or span multiple frameworks), agents write to and read from this sidecar over the Model Context Protocol (MCP). The sidecar is itself an MCP server; agents call its tools exactly the same way they call any other tool!
The server itself is built with distributed environments in mind, and natively handles concurrency, crash resilience and atomic claims in addition to being a common interface for state management between agents.
Features
- Durable Key-Value Store: CRUD operations with optional TTL (Time-To-Live).
- Workflow Lifecycle Registry: Centralised coordination (create, claim, checkpoint, and resume) for distributed multi-agent workers without out-of-band communication.
- TTL Leases & Locks: Concurrency control to prevent race conditions and split-brain scenarios.
- Audit Logging & Session Snapshotting: Audit state transitions and persist session contexts.
- Multiple Backends: SQLite (with WAL mode & serialisation) and high-concurrency Redis currently supported.
Installation
Install the package via pip or your favorite Python package manager:
If you want to use the Redis backend:
Building from Source
To build and install the package from source:
- Clone the repository:
- Install build dependencies:
- Build the wheel and source distribution:
- Install the package locally: Or install the package in editable mode for active development:
Quick Start
Running the Server
In a multi-agent distributed environment, you would typically run the state sidecar as an HTTP SSE service so multiple remote agents and clients can connect to it concurrently.
HTTP SSE Mode (Primary for Distributed Environments)
Start the SSE server to listen on a network port:
By default, the server binds to 0.0.0.0 and listens on port 8000. The MCP endpoint is available at http://localhost:8000/mcp.
Stdio Mode (For Subprocess / Local Agent Execution)
Launch the server via standard input/output:
Configuration
The server is configured entirely using environment variables:
Tool Reference
Group 1 — Key-Value Store
state_set(key, value, ttl_seconds?, agent_id?): Upsert a JSON-serialisable value with optional TTL.state_get(key): Retrieve a value (returnsfound=Falseif missing or expired).state_delete(key): Delete a key.state_list(prefix?): List all live keys, optionally filtered by prefix.
Group 2 — Workflow Lifecycle
workflow_create(name, tags?): Register a workflow; returns a uniquerun_id.workflow_discover(tags?, status?): Find workflows filtered by tags or status.workflow_claim(run_id, agent_id): Atomically claim acreatedworkflow.workflow_checkpoint(run_id, step, output): Persist step output and advance the step counter.workflow_resume(run_id): Get full resume context including last step and all step outputs.workflow_status(run_id): Get lightweight status (status, last step, and timestamps).workflow_list(): List all registered workflows.
Group 3 — Lease & Concurrency Control
lease_acquire(resource_id, holder_id, ttl_seconds): Attempt to acquire an exclusive lock.lease_release(resource_id, holder_id): Voluntarily release a held lease.lease_renew(resource_id, holder_id, ttl_seconds): Extend lease duration without releasing.
Group 4 — Sessions & History
session_save(session_id, context): Save a snapshot of workflow context.session_restore(session_id): Retrieve saved context after crash or handoff.history_log(key?, n?): Retrieve the last N state-transition records with timestamps and writer IDs.
Group 5 — Observability
sidecar_health(): Liveness, backend type, uptime, and database metrics.sidecar_reset(): Irreversibly wipe all data.
License
This project is licensed under the MIT License. See LICENSE for details.
Source: README.md at commit 9a992d0
Tools
0Version history
1- v0.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts