image_describe — Tools for Agents MCP Tool
image_describe
(image describe) is one of 107 tools on the
Tools for Agents
MCP server. Connect the server and your client discovers it on the handshake.
by client
How to call image_describe from your client
- Claude Code Tools for Agents image_describe run in your project directory
- Claude Desktop Tools for Agents image_describe ~/Library/Application Support/Claude/claude_desktop_config.json
- Cursor Tools for Agents image_describe ~/.cursor/mcp.json
- VS Code Tools for Agents image_describe .vscode/mcp.json
- Zed Tools for Agents image_describe ~/.config/zed/settings.json
- Windsurf Tools for Agents image_describe ~/.codeium/windsurf/mcp_config.json
- Cline Tools for Agents image_describe ~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
- Gemini CLI Tools for Agents image_describe ~/.gemini/settings.json
- Grok Tools for Agents image_describe .mcp.json (in your project root)
- ChatGPT Tools for Agents image_describe Settings → Connectors → Advanced → Developer mode
- Claude.ai Tools for Agents image_describe Settings → Connectors → Add custom connector
- LangChain Tools for Agents image_describe pip install langchain-mcp-adapters
Fastest route
claude mcp add --transport http tools-for-agents https://api.toolsforagents.tools/mcpOther tools on this server
- orient
- extract_url
- extract_pdf
- embed_text
- ocr_image
- book_ocr
- validate_email
- crypto_invoke
- html_to_markdown
- x402_info
- list_tools
- web_search
- page_metadata
- page_peek
- extract_outline
- truncate_context
- chunk_text
- text_similarity
- validate_phone
- youtube_transcript
- extract_query
- summarize_text
- rerank_docs
- translate_text
- agent_research
- browser_interact
- read_url
- research_topic
- map_site
- estimate_cost
- memory_store
- memory_search
- validate_url
- extract_links
- json_ld
- readability
- extract_schema
- extract_json
- cache_url
- retrieve
- screenshot
- batch_extract
- crawl
- job_status
- monitor_url
- compare_texts
- ocr_table
- transcribe_audio
- csv_parse
- json_parse
- xml_parse
- markdown_parse
- regex_extract
- keyword_extract
- entity_extract
- sentiment_score
- language_detect
- readability_score
- text_diff
- dedupe_text
- normalize_dates
- content_hash
- pii_detect
- json_flatten
- merge_records
- hash_text
- base64_encode
- base64_decode
- word_stats
- line_split
- extract_emails
- extract_phones
- url_normalize
- pdf_metadata
- pdf_split
- robots_parse
- redirect_trace
- dns_lookup
- ssl_check
- wayback
- rdap
- html_clean
- seo_audit
- page_links_external
- validate_iban
- validate_ip
- validate_domain
- validate_uuid
- ocr_url
- ocr_table_url
- list_chains
- run_chain
- run_mission
- table_extract
- diff_url
- sitemap_parse
- feed_parse
- verify_fact
- plan
- dry_run
- advisor
- crp_resolve
- crp_feedback
- workflow_stateful
- fallback_chain
- source_credibility
This list was read from the server itself, by connecting to it and calling tools/list on 24 September 2026. It is what
the server actually exposes, not what its listing claims.
Mutating and Read-only are read off each tool's name, not its schema — a hint, not a guarantee. The registry stores tool names only; connect the server for its live schemas.