Synapse
Server Details
Codebase memory for AI coding agents: files, lines, callers and tests for any public GitHub repo.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 7 tools
Each tool maps to a distinct stage of the code-understanding workflow (overview, search, read, impact, tests, history, plan). The only real overlap is plan_change, which bundles files/callers that blast_radius and read_code also return, so an agent may occasionally pick plan_change when it wanted a single-purpose tool, but descriptions steer usage well.
All names are snake_case and readable, but the patterns vary: verb_noun (read_code, plan_change), noun (blast_radius, repo_map), verb_adjective (find_existing), noun_preposition (tests_for), and a bare single word (why). It's coherent enough to navigate but not a predictable convention.
Seven tools is tightly scoped and each one clearly earns its place, covering a complete pre-change investigation flow without filler. Nothing looks redundant or missing at the count level.
The surface covers orientation, semantic search, symbol reading, impact analysis, test discovery, and history/reasoning — a solid lifecycle for 'understand before editing'. Minor gaps: no text/grep or symbol-reference search distinct from semantic find_existing, and no way to inspect diffs or recent changes at a repo level.
Available Tools
7 toolsblast_radiusWhat breaks if this changesARead-onlyIdempotentInspect
Every call site of a file or one of its functions, with the calling line of code, plus importers and tests. Use before changing a signature or deleting code.
Inputs: path (required), repository (required), symbol.
find_existingFind existing code to reuseARead-onlyIdempotentInspect
Search existing functions, classes and methods by what they do (e.g. "format currency"). Use before writing a new helper.
Inputs: query (required), repository (required).
plan_changePlan a code changeARead-onlyIdempotentInspect
Call ONCE at the start of a coding task. A complete brief: files and line ranges to change, the key functions in full with their callers, the existing pattern to follow, decisions not to break and the only tests to run. From the code graph, not guesses.
Inputs: task (required), repository (required), paths, terms, +2 more.
read_codeRead one function, or a file outlineARead-onlyIdempotentInspect
Read code without opening whole files. With symbol: just that function, method or class (numbered lines). Without: the file's outline (every declaration with its signature and line range). Use instead of reading a full file.
Inputs: path (required), repository (required), symbol.
repo_mapMap of the repositoryARead-onlyIdempotentInspect
One screen on an unfamiliar repo: main areas with their most used code, entry points, API routes and pages, where tests live, and the stack. Call once instead of exploring folders.
Inputs: repository (required).
tests_forWhich tests to runARead-onlyIdempotentInspect
The test files that cover the given files (direct importers, same-name tests, and tests one import away), so you run only those instead of the whole suite.
Inputs: paths (required), repository (required).
whyWhy is this code like this?ARead-onlyIdempotentInspect
Reasons behind a file or line: decisions from PRs, reviews and reverts, the commit that last changed the line (with its message), the function there and who knows the code. Use before changing or deleting code that looks odd.
Inputs: path (required), repository (required), line.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Code intelligence for LLMs. Analyze, search, and retrieve code from any public git repository.
Codebase intelligence for AI coding agents: graph, git history, docs, decisions, code health.
Shared memory for coding agents. Stop re-explaining your codebase every session.
Codebase intelligence for AI agents — dead code, blast radius, ownership.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides AI coding agents with persistent architectural memory of codebases, enabling impact analysis, test generation, and code generation with reduced token usage.MIT
- AlicenseNot gradedqualityBmaintenanceProvides AI agents with causal code memory by indexing repositories into a graph of symbols and edges, enabling context-aware retrieval of relevant code slices.59 PyPI3MIT
- FlicenseAqualityCmaintenanceGives coding agents a memory of codebases by searching repositories using semantic similarity and structural call/import graphs, enabling reuse of proven patterns and reducing token usage.6-
- AlicenseNot gradedqualityCmaintenanceLocal-first repository memory for AI coding agents that indexes codebases into SQLite and exposes it through MCP tools, with a browser dashboard for architecture inspection.11 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.