Skip to main content
mcpSource-backed
Klavis Strata logo

Klavis Strata MCP Router

Open-source MCP router from Klavis AI that progressively exposes actions from multiple configured MCP servers instead of flooding Claude with every tool.

by Klavis AI · submitted by oktofeesh1·added 2026-06-05·
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://www.klavis.ai/docs/concepts/strata, https://github.com/Klavis-AI/klavis
Brand
Klavis Strata
Brand domain
klavis.ai
Brand asset source
brandfetch
Safety notes
Strata can execute tools on every enabled downstream MCP server; treat it as a privileged router, not a harmless discovery layer., Review each downstream server before adding it, because Strata can route file, browser, database, SaaS, shell, or write-capable actions through one interface., The HTTP/SSE mode starts an ASGI server and the source currently binds uvicorn to all interfaces; restrict network exposure with firewall rules, reverse proxies, or local-only deployment., Store bearer tokens, OAuth credentials, headers, and environment variables in a secret manager or private config file rather than committing Strata configuration., Disable or remove servers that should not be available to a specific project, user, or model session.
Privacy notes
Strata stores configured server names, commands, URLs, headers, and environment variables in a local JSON configuration file., User prompts, action discovery queries, tool schemas, tool arguments, and downstream server responses can all become visible to the MCP client and model provider., Routed tools may expose third-party account data, files, repositories, browser state, database rows, or workspace context depending on which servers are enabled., Hosted Klavis APIs and SDKs are separate from the local open-source router; review Klavis account, API-key, and data-handling terms before using hosted instances.
Author
Klavis AI
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

15 minutes

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

5 prerequisites to line up before setup. Have accounts and credentials ready first.

0/5 ready
Account & credentials1Install & runtime2Configuration1Permissions & scopes115 minutes

Safety & privacy surface

Safety & privacy surface

5 safety and 4 privacy notes across 5 risk areas. Review closely: credentials & tokens, network access, third-party handling.

5 areas
  • SafetyExecution & processesStrata can execute tools on every enabled downstream MCP server; treat it as a privileged router, not a harmless discovery layer.
  • SafetyLocal filesReview each downstream server before adding it, because Strata can route file, browser, database, SaaS, shell, or write-capable actions through one interface.
  • SafetyNetwork accessThe HTTP/SSE mode starts an ASGI server and the source currently binds uvicorn to all interfaces; restrict network exposure with firewall rules, reverse proxies, or local-only deployment.
  • SafetyCredentials & tokensStore bearer tokens, OAuth credentials, headers, and environment variables in a secret manager or private config file rather than committing Strata configuration.
  • SafetyCredentials & tokensDisable or remove servers that should not be available to a specific project, user, or model session.
  • PrivacyLocal filesStrata stores configured server names, commands, URLs, headers, and environment variables in a local JSON configuration file.
  • PrivacyThird-party handlingUser prompts, action discovery queries, tool schemas, tool arguments, and downstream server responses can all become visible to the MCP client and model provider.
  • PrivacyThird-party handlingRouted tools may expose third-party account data, files, repositories, browser state, database rows, or workspace context depending on which servers are enabled.
  • PrivacyCredentials & tokensHosted Klavis APIs and SDKs are separate from the local open-source router; review Klavis account, API-key, and data-handling terms before using hosted instances.

Disclosure: Klavis AI also offers hosted MCP integration APIs and managed Strata services; this entry focuses on the open-source `strata-mcp` router in the public repo.

Safety notes

  • Strata can execute tools on every enabled downstream MCP server; treat it as a privileged router, not a harmless discovery layer.
  • Review each downstream server before adding it, because Strata can route file, browser, database, SaaS, shell, or write-capable actions through one interface.
  • The HTTP/SSE mode starts an ASGI server and the source currently binds uvicorn to all interfaces; restrict network exposure with firewall rules, reverse proxies, or local-only deployment.
  • Store bearer tokens, OAuth credentials, headers, and environment variables in a secret manager or private config file rather than committing Strata configuration.
  • Disable or remove servers that should not be available to a specific project, user, or model session.

Privacy notes

  • Strata stores configured server names, commands, URLs, headers, and environment variables in a local JSON configuration file.
  • User prompts, action discovery queries, tool schemas, tool arguments, and downstream server responses can all become visible to the MCP client and model provider.
  • Routed tools may expose third-party account data, files, repositories, browser state, database rows, or workspace context depending on which servers are enabled.
  • Hosted Klavis APIs and SDKs are separate from the local open-source router; review Klavis account, API-key, and data-handling terms before using hosted instances.

Prerequisites

  • Python 3.10 or newer, matching the open-strata package metadata.
  • pipx or pip available on the machine that will run the router.
  • One or more MCP servers you already trust and are authorized to connect.
  • Any API keys, OAuth credentials, headers, or environment variables required by the downstream MCP servers.
  • A plan for where Strata should store its MCP server configuration file.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
15 minutes
Difficulty
intermediate
Tool listing metadata
Disclosure
Klavis AI also offers hosted MCP integration APIs and managed Strata services; this entry focuses on the open-source `strata-mcp` router in the public repo.
Full copyable content
{
  "mcpServers": {
    "strata": {
      "command": "strata"
    }
  }
}

About this resource

Content

Klavis Strata is an open-source MCP router that sits between Claude and a set of configured MCP servers. Instead of exposing every downstream tool at once, it provides a smaller set of discovery, inspection, execution, documentation search, and authentication helper tools.

The open-source implementation lives under open-strata in the Klavis repository and is published as the strata-mcp Python package. It can run in stdio mode for local MCP clients or in HTTP/SSE mode for deployments that need a network transport.

Source Review

These sources were reviewed on 2026-06-05. Prefer the live repository, open-strata README, package metadata, router source files, PyPI metadata, and Klavis docs for current install commands, router modes, tool names, supported transports, and hosted-service boundaries.

Features

  • Discover available actions across configured downstream MCP servers.
  • Retrieve detailed tool schema and parameter information before execution.
  • Execute a selected action on a selected downstream server.
  • Search server documentation by keyword.
  • Handle authentication failure flows for configured servers.
  • Add, list, enable, disable, and remove downstream MCP server configurations through the strata CLI.
  • Run as a stdio MCP server for local clients.
  • Run as an HTTP/SSE router when a network transport is required.
  • Watch the configuration file and sync enabled server connections while running.

Installation

Install the open-source router package:

pipx install strata-mcp

Add trusted downstream MCP servers with the Strata CLI. For example, a stdio server can be registered by name:

strata add --type stdio playwright npx @playwright/mcp@latest

Then configure Claude to launch Strata:

{
  "mcpServers": {
    "strata": {
      "command": "strata"
    }
  }
}

For HTTP or SSE downstream servers, use private endpoint placeholders and secret-managed headers rather than committing real bearer tokens or URLs into project files.

Use Cases

  • Keep Claude's visible tool list smaller when a project uses many MCP servers.
  • Discover which downstream server action is relevant before executing it.
  • Route several trusted stdio and HTTP MCP servers behind one local MCP entry.
  • Search tool documentation before calling a risky or unfamiliar action.
  • Temporarily disable servers that should not be available in a given project.
  • Experiment with progressive tool discovery for agent workflows.

Safety and Privacy

Strata concentrates access to many downstream tools. That is useful for context management, but it also means one MCP server entry can route to high-impact actions across files, browsers, SaaS APIs, databases, developer tools, and other systems. Audit each downstream server independently and keep the enabled set as small as the task allows.

The open-source source code stores server configuration in a local JSON file and supports headers and environment variables for downstream servers. Treat this configuration as sensitive. The HTTP/SSE router mode should be deployed behind appropriate network controls because it can expose access to every enabled server action.

Duplicate Check

No Klavis-AI/klavis, strata-mcp, Klavis Strata, or matching source URL was found in content/mcp.

Source citations

Add this badge to your README

Show that Klavis Strata MCP Router is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/klavis-strata-mcp-router.svg)](https://heyclau.de/entry/mcp/klavis-strata-mcp-router)

How it compares

Klavis Strata MCP Router side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field

Open-source MCP router from Klavis AI that progressively exposes actions from multiple configured MCP servers instead of flooding Claude with every tool.

Open dossier

Open-source MCP servers for accessing ACI.dev managed functions through app-specific tools or a unified search-and-execute interface.

Open dossier

Remote Agentage Memory MCP server giving Claude one shared, portable memory across every AI you use - search, read, write, edit, list, and delete plain Markdown notes you own, over Streamable HTTP with OAuth 2.1.

Open dossier

Apache-2.0 agentic proxy that can expose stdio, HTTP, SSE, and Streamable HTTP MCP servers through a managed gateway with federation, OAuth/JWT authentication, RBAC/CEL policy, CORS, TLS, observability, and Kubernetes Gateway API support.

Open dossier
Next steps
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersoktofeesh1oktofeesh1vreshchoktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
BrandKlavis Strata logoKlavis StrataACI.dev logoACI.devAgentage Memory logoAgentage Memoryagentgateway logoagentgateway
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorKlavis AIAipolabsagentageagentgateway
Added2026-06-052026-06-052026-06-182026-06-06
Platforms
Harness
Source repo
Safety notesStrata can execute tools on every enabled downstream MCP server; treat it as a privileged router, not a harmless discovery layer. Review each downstream server before adding it, because Strata can route file, browser, database, SaaS, shell, or write-capable actions through one interface. The HTTP/SSE mode starts an ASGI server and the source currently binds uvicorn to all interfaces; restrict network exposure with firewall rules, reverse proxies, or local-only deployment. Store bearer tokens, OAuth credentials, headers, and environment variables in a secret manager or private config file rather than committing Strata configuration. Disable or remove servers that should not be available to a specific project, user, or model session.The unified server can discover and execute many ACI.dev managed functions, so restrict permissions before connecting it to an autonomous agent. App-specific servers should be preferred when a workflow only needs a small set of integrations. Connected apps may read, create, update, delete, or send data depending on the selected functions and linked account permissions. Require human approval before email, calendar, CRM, ticketing, infrastructure, billing, deployment, or account-administration actions.The memory__write, memory__edit, and memory__delete tools create, modify, and remove your stored notes; review actions before granting broad access.Agentgateway can aggregate and expose many downstream MCP targets through one endpoint; every target's permissions become part of the gateway surface. Stdio targets are spawned by the gateway process, so commands such as package runners or containers inherit the gateway host's trust boundary. Demo configs use permissive CORS and local authorization servers; lock down origins, headers, issuers, audiences, JWKS, and resource metadata before production use. CEL/RBAC policies can inspect MCP tool names, arguments, results, prompts, resources, request bodies, JWT claims, API keys, and backend metadata; test policies before relying on them. Remote MCP proxying, OAuth provider adaptation, Kubernetes routing, TLS termination, and guardrails are infrastructure changes that should go through normal security review.
Privacy notesStrata stores configured server names, commands, URLs, headers, and environment variables in a local JSON configuration file. User prompts, action discovery queries, tool schemas, tool arguments, and downstream server responses can all become visible to the MCP client and model provider. Routed tools may expose third-party account data, files, repositories, browser state, database rows, or workspace context depending on which servers are enabled. Hosted Klavis APIs and SDKs are separate from the local open-source router; review Klavis account, API-key, and data-handling terms before using hosted instances.Tool names, function arguments, prompts, linked account identifiers, execution results, logs, and connected-service data may pass through ACI.dev, the selected third-party apps, the MCP client, and the model provider. API keys and linked-account credentials must be protected in client config, environment files, logs, screenshots, and shared prompts. Review ACI.dev account, tenant, retention, audit-log, and OAuth settings before routing production or customer data through the server.Notes you read or write are stored server-side in your Agentage Memory and mirrored locally as Markdown you can export anytime; note contents pass through model context.MCP requests, tool arguments, tool results, prompt names, resource names, session IDs, JWT/API-key claims, raw request/response bodies, logs, traces, and telemetry may pass through the gateway. CEL policy and observability features may buffer or inspect request and response bodies depending on configuration. OAuth/JWT metadata, bearer tokens, API keys, DCR secrets, Keycloak/Auth0/Okta settings, and upstream MCP credentials must be protected as secrets. Any data returned by downstream MCP tools can still be sent onward by the MCP client to the configured model provider.
Prerequisites
  • Python 3.10 or newer, matching the open-strata package metadata.
  • pipx or pip available on the machine that will run the router.
  • One or more MCP servers you already trust and are authorized to connect.
  • Any API keys, OAuth credentials, headers, or environment variables required by the downstream MCP servers.
  • ACI.dev account, API key, and linked account owner ID.
  • Connected app credentials or linked accounts for the tools the agent should use.
  • MCP client that can launch Python package commands with environment variables.
  • Clear allowlist of apps, functions, and user accounts before exposing write-capable tools.
  • agentage account (sign in at memory.agentage.io)
  • OAuth 2.1 authentication (PKCE + Dynamic Client Registration, handled in the connect flow)
  • Network access to memory.agentage.io (HTTPS required)
  • Claude Desktop 0.7.0+ or Claude Code with MCP (HTTP transport) support
  • Agentgateway binary, container image, or source checkout from the upstream release/container/docs path.
  • At least one downstream MCP target, such as a stdio command, remote MCP server, SSE server, or Streamable HTTP server.
  • MCP client that can connect to the exposed Streamable HTTP or SSE route.
  • Auth, CORS, TLS, route, and policy configuration reviewed before shared or remote exposure.
Install
pipx install strata-mcp
uvx aci-mcp unified-server --linked-account-owner-id YOUR_LINKED_ACCOUNT_OWNER_ID
claude mcp add --transport http agentage-memory https://memory.agentage.io/mcp && claude mcp list
docker pull ghcr.io/agentgateway/agentgateway
Config
{
  "mcpServers": {
    "strata": {
      "command": "strata"
    }
  }
}
{
  "mcpServers": {
    "aci": {
      "command": "uvx",
      "args": [
        "aci-mcp",
        "unified-server",
        "--linked-account-owner-id",
        "YOUR_LINKED_ACCOUNT_OWNER_ID"
      ],
      "env": {
        "ACI_API_KEY": "YOUR_ACI_API_KEY"
      }
    }
  }
}
{
  "mcpServers": {
    "agentage-memory": {
      "url": "https://memory.agentage.io/mcp",
      "type": "http"
    }
  }
}
{
  "mcpServers": {
    "agentgateway": {
      "url": "LOCAL_AGENTGATEWAY_MCP_URL",
      "headers": {
        "Authorization": "Bearer AGENTGATEWAY_MCP_TOKEN"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.