Manufact
Product▾
- MCP HostingDeploy MCP apps and servers to production.
- Cross-client testingRun the same checks across ChatGPT, Claude, and more.
- Publishing checksAudit your MCP app against ChatGPT Apps Store and Cloud Connectors requirements.
- Submission PackGenerate the assets you need for marketplace submission.
- Cloud InspectorTrace, replay, and debug MCP traffic in production.
- Public chatEmbeddable chat surfaces for your product.
- AnalyticsUsage, latency, and reliability in one place.
- Products
- Cloud
- mcp-use SDK
- Inspector
- Vibe
Developers▾
- Manufact docsBuild, deploy, and operate on Manufact Cloud.
- SupportCommunity, issue reporting, and premium support.
- TemplatesStart from a deploy-ready MCP framework template.
- mcp-use docsBuild MCP apps and servers with the mcp-use SDK.
- mcp-use Inspector DocsInspect and debug MCP servers from your browser.
- mcp-use client CLIConnect to and call MCP servers from your terminal.
- MCP server tunnelingExpose a local MCP server through a secure tunnel.
- Pricing
- Blog
Open Targets
mcp.platform.opentargets.org/mcp
Good
Protocol
Tools
All tools have descriptions
All tools have non-empty descriptions
All tools have OpenAI behavior hints
10 behavior annotation issue(s) found
How to fix: On each tool, declare annotations.readOnlyHint, annotations.destructiveHint, and annotations.openWorldHint as booleans. The policy review separately assesses whether their values match the tool's actual behavior.
Tool input header annotations are valid
All x-mcp-header annotations satisfy Streamable HTTP requirements
Tool input schemas have a valid object structure
All tool input schemas have a valid object structure
Tool names use valid characters
All tool names use valid characters
Tool names follow the MCP 1–128 character range
All tool names follow the MCP recommended length
Tool names follow MCP uniqueness guidance
All tool names are unique
Declared output schemas have a valid basic structure
5 declared output schema(s) pass basic structural validation; schemas may describe any JSON value, including arrays
Tool text has no hidden control characters
No invisible or control characters found in tool-facing text
Tool invocation metadata present
No view resources found — view checks skipped
Tool-linked resource URI is readable
No view resources found — view checks skipped
Tool visibility metadata is valid
No view resources found — view checks skipped
MCP Apps
View resource envelope is valid
No view resources found — view checks skipped
All discovered view resources were inspected
No view resources found — view checks skipped
View resources declare a domain
No view resources found — view checks skipped
View resource metadata complete
No view resources found — view checks skipped
CSP metadata covers literal external origins
No view resources found — view checks skipped
Declared domains respond
No view resources found — view checks skipped
Client compatibility
Skills over MCP resources are readable
Server does not advertise the Skills over MCP extension
Claude Code metadata fits its 2 KB fields
3 metadata field(s) exceed Claude Code's 2 KB truncation point
How to fix: Keep each tool description and the server instructions field at or below 2 KB, and put critical guidance first.
Claude tools declare applicable behavior hints
All tools include an applicable readOnlyHint or destructiveHint
All tools have a display title
5 tool(s) missing a display title: get_open_targets_graphql_schema, get_type_dependencies, search_entities, query_open_targets_graphql, batch_query_open_targets_graphql
How to fix: Set the top-level tool.title to a short human-readable label (for example, "Search catalog"). Claude directory submission requires tool titles; annotations.title remains accepted only as a legacy fallback.
Claude tool names are within 64 characters
All tool names are within Claude's 64-character limit
Cursor tool-name budget advisory
No tool name independently exhausts Cursor's observed 60-character combined budget
ChatGPT tool names are unique
All tool names are unique
OpenAI file parameters use valid schemas
All declared OpenAI file parameters use reviewer-valid schemas
Overview
- Author
- OpenTargets
- Verification
- partner
- Auth
- None — public endpoint
- Categories
- datalife-sciences
- Works with
- claudeclaude-apiclaude-code
- Docs
- Documentation
get_open_targets_graphql_schemasearch_entitiesquery_open_targets_graphqlbatch_query_open_targets_graphqlRelated MCP servers
FAQ
Open Targets install, tools, readiness, and alternatives.
How do I add Open Targets to Claude, ChatGPT, or Cursor?
Add Open Targets to Claude, ChatGPT, or Cursor by connecting its remote MCP URL in each client's MCP settings. In Claude, add a custom connector. In ChatGPT, add an MCP app. In Cursor, add an MCP server under Settings. The MCP URL is https://mcp.platform.opentargets.org/mcp.
Is Open Targets MCP ready for ChatGPT and Claude?
As of September 15, 2026, Open Targets scores 84/100 on Manufact's MCP publishing checklist. The scan does not yet meet ChatGPT publishing checks and does not yet meet Claude publishing checks.
What tools does the Open Targets MCP server provide?
Open Targets provides these MCP tools: get_open_targets_graphql_schema, search_entities, query_open_targets_graphql, and batch_query_open_targets_graphql.
What are the best alternatives to Open Targets?
As of September 15, 2026, alternatives to Open Targets in data on the Manufact MCP catalog include MoSPI and Wolfram.
Does Open Targets MCP require authentication?
Open Targets does not require authentication. It is a public MCP endpoint you can connect without logging in.
Who develops Open Targets?
Open Targets is developed by OpenTargets. It is listed as partner on the Claude connector directory.
Not your MCP?
Scan any public or OAuth MCP URL against ChatGPT and Claude publishing checks. No account required.