OpenRath — Watchlist | MCP100 Index

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Track runtime adapters and protocol support as OpenRath develops

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Production-oriented multi-agent workflows with durable sessions and memory

What we know

Session-first Python agent framework/runtime for workflows, tools, memory, sandboxes and production execution.

Maintenance / activity evidence

Observed Sep 28, 2026 (UTC)docs: redraw the README diagrams as SVG ( 68)

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Activity source · commits ↗Activity source · releases ↗

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Tenant/project/policy boundaries are operator-defined. Writes: Custom tool/workflow side effects.
Explicit-grant server tokens.
Sensitive access: Depends on tools/backends

Durable execution and custom tools require explicit grants and deployment policy.

Security source · repository notice ↗

Full authority, access and evidence limits are available in Review context and Access & risk.

Popularity

959 repository stars

Stars observed Oct 6, 2026.

30-day package downloads intentionally left null because the package-stats provider ran out of credits during Batch 3 QA.

All limitations / Review context

Which MCP integrations and agent execution paths are documented now?

The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.

Durable execution and custom tools require explicit grants and deployment policy.
Tenant/project/policy boundaries are operator-defined.
Explicit-grant server tokens.
Sessions, memory, checkpoints and artifacts can persist.
Reviewed write actions: Custom tool/workflow side effects
Sensitive access: Depends on tools/backends
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.
No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
The fetched official SECURITY.md path returned HTTP 404; it was not treated as positive evidence.
Exact server endpoint/token issuance
Pricing
Agent Server HTTP is beta.
Production profile requires migration.

Original activity observations

2026-09-28T07:04:56Z: docs: redraw the README diagrams as SVG ( 68)

Technical identity

github.com/rath-team/openrath

Exact implementation source: https://github.com/rath-team/openrath ↗
Reviewed resource type: Framework
Repository identity: Rath-Team/OpenRath
Package identity: pypi:openrath

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 6, 2026

GitHub repository ↗
rath-team/openrath
Recorded repository material and project history.
Includes references whose attribution is not established.

Setup · Watchlist

Framework setup

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
OpenRath is a Python agent framework, not a ready-made MCP service.
package install · Publisher instructions
pip install openrath
Configure / authenticate
MCP100 setup guide
Install Python/package; configure an LLM API key and run the documented example/01_hello_agent.py in the source repository to learn the framework. Optional extras [opensandbox], [openviking] are separate.
Check connection
Suggested check
Import openrath or run the first example with a test provider key.
Remove / uninstall / revoke
MCP100 setup guide
Remove the Python package in the same environment using `python -m pip uninstall openrath`; stop any separately deployed OpenRath server first. Do not delete .openrath/memory without a separate data-retention decision.
Client unregistration, program uninstall, persistent-data deletion, and credential revocation must be treated separately.
Package / application uninstall · matching installation environment · MCP100 composed guide
python -m pip uninstall openrath

Official Documentation & Sources

What it does

Session-first Python agent framework/runtime for workflows, tools, memory, sandboxes and production execution.

Capability: AI & Reasoning
Resource type: Framework
Best fit: Production-oriented multi-agent workflows with durable sessions and memory

Representative uses

Compose multi-agent workflows
Wrap stdio MCP tools
Persist memory
Run durable server workflows

Limitations

Agent Server HTTP is beta.
Production profile requires migration.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Explicit-grant server tokens.
Permissions: Tenant/project/policy boundaries are operator-defined.
Data handling: Sessions, memory, checkpoints and artifacts can persist.
Cost: unknown
Risk and cautions: Durable execution and custom tools require explicit grants and deployment policy.

Access scope and cautions

Write actions: Custom tool/workflow side effects
Sensitive access: Depends on tools/backends
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Compose multi-agent workflows; Wrap stdio MCP tools; Persist memory; Run durable server workflows.

What setup and authentication are documented?

Recorded installation/entrypoint step: pip install openrath. Recorded transport: other. Prerequisites: Python; PostgreSQL for server profile. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Agent Server tokens with explicit action grants.

Can it modify data or perform write operations?

Documented write actions include: Custom tool/workflow side effects. Recorded permission boundary: Tenant/project/policy boundaries are operator-defined.

What data-handling boundary should I consider?

Sessions, memory, checkpoints and artifacts can persist. Recorded sensitive-access context: Depends on tools/backends.

What limitations and risks should I check before use?

Durable execution and custom tools require explicit grants and deployment policy. Agent Server HTTP is beta. Production profile requires migration. A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.

Is this an official MCP?

Rath-Team is listed as Community implementation in MCP100’s current evidence.