lightdash_mcp

Provides an MCP (Model Context Protocol) server that connects AI assistants to Lightdash to support discovery of projects/explores/schemas, execution of queries, and CRUD-style management of charts, dashboards, tiles, and spaces—primarily via Lightdash REST endpoints using a personal access token, with optional support for auth frontends such as Cloudflare Access and Google Cloud IAP.

Evaluated Mar 30, 2026 (0d ago)
Homepage ↗ Repo ↗ Ai Ml mcp lightdash analytics business-intelligence data-visualization python
⚙ Agent Friendliness
59
/ 100
Can an agent use this?
🔒 Security
59
/ 100
Is it safe for agents?
⚡ Reliability
31
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
75
Error Messages
0
Auth Simplicity
65
Rate Limits
10

🔒 Security

TLS Enforcement
85
Auth Strength
70
Scope Granularity
35
Dep. Hygiene
55
Secret Handling
45

Uses a Lightdash Personal Access Token and supports passing through Authorization. The README provides operational guidance for 401/connection errors, but does not document tool-level authorization boundaries or rate limits. Secret handling guidance warns against committing .mcp.json containing secrets. TLS enforcement is not explicitly stated, but LIGHTDASH_URL examples use HTTPS. Dependency list is minimal in the manifest snippet; no CVE/SBOM data is provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
50
Error Recovery
40
AF Security Reliability

Best When

You already have a Lightdash instance and want an AI agent to programmatically inspect and manage analytics artifacts (charts/dashboards) with an MCP client (e.g., Claude Desktop/Code).

Avoid When

You cannot safely store and protect LIGHTDASH_TOKEN (or related IAP credentials), or you require explicit documented rate-limit behavior and strict SLAs.

Use Cases

  • Letting LLMs explore available Lightdash datasets (projects/explores) and understand schemas
  • Automatically creating/updating Lightdash charts and dashboards from natural-language intent
  • Running query executions for specific charts/dashboards/tiles and returning results to an agent
  • Programmatic organization of Lightdash content using spaces

Not For

  • Replacing Lightdash as the primary UI for end users who do not want automation
  • Handling sensitive analytics without access controls and careful secret management
  • High-scale public workloads where unauthenticated requests could be made to the MCP server

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Lightdash Personal Access Token via LIGHTDASH_TOKEN (mapped to HTTP Authorization: ApiKey as described) Optional Google Cloud IAP JWT signing (IAP_ENABLED + related service-account/ADC env vars) with Proxy-Authorization: Bearer <jwt> Optional Cloudflare Access (CF_ACCESS_CLIENT_ID / CF_ACCESS_CLIENT_SECRET)
OAuth: No Scopes: No

Authentication is centered on a Lightdash Personal Access Token; optional IAP/Cloudflare settings are supported for environments behind those access layers. The README does not describe fine-grained scopes in terms of MCP tool permissions.

Pricing

Free tier: No
Requires CC: No

No pricing for the MCP server is stated in the provided content; cost likely depends on your Lightdash plan and any cloud/access-layer usage (e.g., IAP/JWT signing).

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • State-changing tool calls (create/update/delete) are likely not idempotent; agents should avoid automatic retries without safeguards.
  • Credentials in MCP client config files (e.g., .mcp.json) risk leakage if not gitignored.
  • The server requires LIGHTDASH_TOKEN and LIGHTDASH_URL; incorrect/expired tokens will lead to 401 errors.
  • If your Lightdash instance is behind Cloudflare Access or Google IAP, you must set the corresponding environment variables or connectivity/auth will fail.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for lightdash_mcp.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

6533
Packages Evaluated
19870
Need Evaluation
586
Need Re-evaluation
Community Powered