28 MCP Tools in One Connection: A Developer's Field Guide

Spiderbrain's MCP server exposes 28 tools for codebase work, organized into structural queries, memory tree access, and blueprint operations. The developer emphasizes a 'moment-based' dispatch pattern, where tools are called based on workflow situations like new project or refactoring, rather than data model operations. This approach, they argue, is more effective than having many tools without clear dispatch logic.

Model Context Protocol MCP lets an AI agent call structured tools instead of guessing from raw text dumped into a context window. Fine in theory — but most MCP integrations just expose "read file" and "search," which barely improves on copy-pasting code into a chat window. The real question: what tools should an agent actually have access to, for codebase work specifically? Spiderbrain's MCP server exposes 28 tools, split into three functional groups: Structural queries a flat context window literally cannot answer: blast radius path // reach, callers, transitive impact score summary // keystones, blindspots, node scores communities // clusters, boundary edges, paths insights area // summaries, diffs, navigation, search Access to the Memory Tree — a project's accumulated decisions and constraints, persisted across sessions: memory recall files // scoped brief for current context memory search query // semantic search over the full tree memory add node // write with explicit user ratification memory browse scope // browse by scope or recency spiderbrain blueprint read // current nodes, edges, annotations spiderbrain blueprint draw // AI proposes canvas edits — requires human acceptance Don't call all 28 on every turn — that's noise, not context. Here's the practical dispatch table: | Situation | Call | |---|---| | New project | score summary + top spikescore 10 | | Before editing a file | node path + blast radius path | | Session start | memory recall files | | Planning a refactor | communities + boundary edges | | Onboarding to unfamiliar code | blueprint read + insights area | This mapping matters more than tool count. An agent with 28 tools and no dispatch logic will either call none of them or call all of them — both are worse than an agent with 5 tools it actually reaches for at the right moment. The pattern that generalizes beyond this specific server: structure your MCP tools around the moments in a workflow, not around your data model. "New project," "before editing," "session start," "refactor," and "onboarding" are moments a developer or agent actually hits. "Get node," "get edge," "get community" are just database operations wearing a tool-call costume. Link : https://spiderbrain.ai/ https://spiderbrain.ai/ Linkedin : https://www.linkedin.com/company/spiderbrain https://www.linkedin.com/company/spiderbrain Discuss: has anyone else settled on a "moment-based" tool dispatch pattern for their own MCP servers? Curious what situations you gate on.