Engram gives your AI agent the context it can’t see in the code alone.
Most developer tooling work still happens through a UI a human drives. Engram MCP server moves it into the conversation instead. Engram gives your AI agent the context it can’t see in the code alone.
Installation goes through your MCP client rather than a global install: point it at @spectra-g/engram-adapter on npm and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.
The server publishes 13 tools. What each one is for:
Local-First — ** All processing happens on your local hardwareWhat — ** Mines git history to find files that are frequently committed alongside your target fileWhy — ** To reveal hidden dependencies. If A.ts and B.ts changed together 40 times in the last year, your AI needs to know about B.ts before editing A.tsRust — ** Native #[test]Name — ** engramType — ** commandCommand — ** npx -y @spectra-g/engram-adapterCoupling — If "High" or "Critical" risk files are returned, evaluate if they are functionally relatedAction — * Read the file (read_file) if it poses a logical regression riskIgnore — * Skip files that appear coincidental (e.g., lockfiles, gitignore, bulk formatting updates)Memories — Pay close attention to any "Memories" returned in the analysis summaryTests — If test_intents are present, treat them as strict behavioural constraints. If absent, proceed with standard code analysisAmong the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Engram's toolset — Local-First, What, Why and 10 more — is a fair guide to whether it matches your workflow. It is maintained by spectra-g; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Engram's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Local-First | ** All processing happens on your local hardware. |
| What | ** Mines git history to find files that are frequently committed alongside your target file. |
| Why | ** To reveal hidden dependencies. If A.ts and B.ts changed together 40 times in the last year, your AI needs to know about B.ts before editing A.ts. |
| Rust | ** Native #[test] |
| Name | ** engram |
| Type | ** command |
| Command | ** npx -y @spectra-g/engram-adapter |
| Coupling | If "High" or "Critical" risk files are returned, evaluate if they are *functionally related*. |
| Action | * Read the file (read_file) if it poses a logical regression risk. |
| Ignore | * Skip files that appear coincidental (e.g., lockfiles, gitignore, bulk formatting updates). |
| Memories | Pay close attention to any "Memories" returned in the analysis summary. |
| Tests | If test_intents are present, treat them as strict behavioural constraints. If absent, proceed with standard code analysis. |
| Cursor | Settings > General > MCP Servers > Add New MCP Server: - **Name:** engram - **Type:** command - **Command:** npx -y @spectra-g/engram-adapter --- |
{
"mcpServers": {
"engram": {
"command": "npx",
"args": ["-y", "@spectra-g/engram-adapter"]
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.