zed-mcp-server-markitdown

Provides an MCP server integration for Zed that exposes a `convert_to_markdown(uri)` tool to convert documents (PDF/DOCX/XLSX/PPTX), images (with OCR), audio (with transcription), web pages (URLs), structured data (CSV/JSON/XML), and ZIP archives into AI-consumable Markdown context via MarkItDown.

Evaluated Mar 30, 2026 (21d ago)
Repo ↗ Ai Ml mcp zed markitdown document-conversion ocr transcription markdown rust python assistant-context
⚙ Agent Friendliness
50
/ 100
Can an agent use this?
🔒 Security
39
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
65
Error Messages
0
Auth Simplicity
90
Rate Limits
20

🔒 Security

TLS Enforcement
70
Auth Strength
20
Scope Granularity
15
Dep. Hygiene
35
Secret Handling
60

The tool accepts user-controlled URIs (`http(s):`, `file:`, `data:`), which can introduce SSRF/local-file disclosure risks depending on MCP server implementation and Zed’s sandboxing. TLS enforcement is assumed for network calls but not specified. No auth/scopes are documented, so access control is unclear. README mentions runtime installation/downloads (e.g., ONNX/model assets), which increases the importance of dependency and supply-chain review. Secret handling is not discussed in the provided README.

⚡ Reliability

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

Best When

You want a local/offline-friendly document-to-text normalization step in Zed’s Assistant workflow using MCP, especially for heterogeneous file types that need to become Markdown context.

Avoid When

You need strict access controls over what URIs/files can be fetched, or you cannot tolerate dependency/runtime downloads (e.g., model assets) during first run.

Use Cases

  • Convert PDFs/reports into summarizable Markdown
  • Extract key data from spreadsheets (top rows/entries)
  • Summarize articles from HTTP/HTTPS URLs
  • Run OCR on images (JPG/PNG/GIF) and convert extracted text to Markdown
  • Transcribe and convert audio (MP3/WAV) to Markdown
  • Convert CSV/JSON/XML into Markdown for downstream reasoning
  • Ingest ZIP archives containing multiple supported files for combined analysis

Not For

  • Use as a secure content gateway without considering SSRF/local-file access risks from arbitrary `uri` inputs
  • High-assurance production deployments without reviewing MarkItDown and MCP server security/behavior
  • Streaming/real-time conversion pipelines where long-running conversions may time out

Interface

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

Authentication

OAuth: No Scopes: No

No authentication mechanism is described for the MCP tool. Access control (if any) would be handled by the MCP host (Zed) or by the underlying MCP server implementation, which is not detailed in the provided README.

Pricing

Free tier: No
Requires CC: No

No pricing information provided; this appears to be an open-source/local extension.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Tool accepts arbitrary `uri` values including `data:`; agents should avoid passing untrusted or overly broad URIs without safeguards
  • First-run environment warm-up and dependency downloads may exceed Zed startup limits (README mentions potential timeouts and a warm-up step)
  • Python 3.14/Arch dependency conflicts may occur; README suggests a workaround via `uvx` and Python 3.13

Alternatives

Full Evaluation Report

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

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.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered