Discover briefly
List MCP tools as compact summaries instead of injecting every schema.
ToolCapsule keeps schema-heavy MCP servers out of the context window by turning them into lazy-loaded, file-first Agent Skills with patch-and-retry recovery.
The problem
Native MCP is excellent for small, frequent tools. But document and workflow MCP servers often expose long descriptions, schemas, and rules that can be visible to the model even when the user is only planning.
ToolCapsule keeps MCP as the capability layer and uses Skills as the agent-facing workflow layer. Full schemas are still available, but no longer need to be carried every turn.
The capsule
Instead of asking the model to regenerate a large tool call after a failure, ToolCapsule stores the arguments, payloads, request, response, and error as local files.
args.json
content.md
request.json
response.json
error.txt
command.txt
List MCP tools as compact summaries instead of injecting every schema.
Put Markdown, JSON, and long arguments into files the agent can patch.
Run the MCP tool through a CLI and save the full request/response trace.
Fix the local file and replay the same tool call without rewriting the prompt.
Native MCP
ToolCapsule
args.json and content files.For heavy MCP servers
ToolCapsule is designed for Feishu/Lark, Notion, Jira, Linear, Confluence, GitHub management tools, and internal SaaS MCPs.
Start with ToolCapsule