Engram is an MCP server with 17 tools an agent can call, among them engram_close_session, engram_cross_pollinate, engram_delete_memory. It answers at https://api.engram.tools/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 23 September 2026; the last check, on 7 November 2026, succeeded.
Memory for AI agent teams across tools, sessions, repositories, and teammates.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
engram_close_session | Finish an exact journal at a real completion or handoff. Unlike engram_reflect, this atomically closes the session after saving a supplied final summary or confirming an existing checkpoint. Durable memories and journal history remain; clos Inputs: session_id, summary |
engram_cross_pollinate | Reuse a lesson solved in another repository before rebuilding a shared pattern. Unlike engram_recall or engram_smarter, this explicitly excludes target_repo from source searches and adds transfer lessons and quality gates. Returns Markdown Inputs: target_repo, context, session_id, source_repos, include_public, limit |
engram_delete_memory | Preview or permanently erase one private memory and its explicit derived patterns from the live database. Unlike engram_retract_memory, execution cannot be undone. Requires a human workspace OWNER API key; OAuth agents and member keys canno Inputs: memory_id, dry_run, confirmation |
engram_get_context | Audit repository knowledge by category: conventions, gotchas, patterns, solutions and architecture. Unlike engram_recall or engram_smarter, this searches each category separately and returns five sample arrays for coverage review, rather th Inputs: repo, file, task |
engram_list_sessions | Find an exact session_id before recovery, closing or a handoff. Unlike engram_rehydrate, this lists bounded metadata without replaying journal content or changing a session. Returns JSON sessions with member/client attribution, status, acti Inputs: repo, scope, status, agent_tool, member_id, limit |
engram_proof | Audit adoption before a rollout or when checking whether the workspace is using memory and reporting outcomes. Takes no arguments. Returns JSON with memory-bank breakdowns, learning-loop activity, proof points and a benchmark checklist. Doe |
engram_recall | Answer one concrete question from authenticated workspace/public memory before deciding or debugging. Unlike engram_smarter, this retrieves question-specific evidence without task checklists; unlike engram_get_context, it returns one ranked Inputs: query, repo, type, tags, session_id, limit |
engram_reflect | Checkpoint a milestone or handoff for later recovery with engram_rehydrate. Supply at least one of summary, learnings, used_memories or feedback. Returns Markdown with stored/skipped counts, outcomes and next actions. Use engram_store for o Inputs: repo, task, session_id, summary, agent_tool, store |
engram_rehydrate | Recover interrupted work after compaction, resume or lost context. Returns Markdown checkpoints, decisions, gotchas, open loops and recent events. Unlike engram_start, this restores the prior journal when available; unlike engram_recall or Inputs: session_id, agent_tool, project, repo, task, reason |
engram_report_outcome | Record whether a recalled memory helped; returns a confirmation. Use its exact memory_id and evidence in detail. success=false may include failure_reason; outdated marks obsolete knowledge, while success raises confidence. Only accessible w Inputs: memory_id, success, detail, failure_reason, repo, session_id |
engram_restore_memory | Make an explicitly retracted private memory available again. Unlike engram_store, this restores the original ID/content; storing matching retired content returns 409 rather than silently reviving it. Returns JSON memory_id, ACTIVE status an Inputs: memory_id |
engram_retract_memory | Withdraw an exact private memory that should no longer guide agents. Unlike engram_store with supersedes_memory_ids, this needs no replacement and keeps the content for explicit restoration. Unlike engram_delete_memory, it is reversible. Re Inputs: memory_id, reason |
engram_setup | Explain onboarding and inspect the authenticated workspace when an agent needs setup guidance. Returns one JSON response with plan/counts/limits, tool groups, activation checklist and suggested calls; no pagination or installation. Hints pe Inputs: agent_tool, project, repo, role, market, task |
engram_skill | Find a procedural checklist before a repeatable task. Omit skill or pass an empty string to list available names; otherwise load a name such as code-review or skill:code-review. Returns JSON with available_skills/usage for listing or skill/ Inputs: skill |
engram_smarter | Brief a materially different task within the same session. Unlike engram_recall, this combines goal-focused memories with optional procedural checklists; unlike engram_get_context, it ranks evidence for the task instead of returning categor Inputs: context, repo, file, include_skills, session_id, limit |
engram_start | Begin meaningful work in a repository with a Markdown briefing: session id, ranked private/public memory, workspace guidance and optional checklists. Unlike engram_smarter, this includes workspace onboarding/activation guidance; unlike engr Inputs: session_id, agent_tool, project, repo, role, market |
engram_store | Save one durable lesson privately for future workspace agents; returns a confirmation. Use engram_reflect for a milestone with several lessons/outcomes and engram_report_outcome to assess an existing memory. To correct knowledge, supply the Inputs: type, content, repo, tags, agent_tool, session_id |
Every block below points at https://api.engram.tools/mcp. Pick your client and copy.
claude mcp add --transport http engram https://api.engram.tools/mcp
{
"mcpServers": {
"engram": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.engram.tools/mcp"]
}
}
}{
"mcpServers": {
"engram": {
"url": "https://api.engram.tools/mcp"
}
}
}{
"servers": {
"engram": {
"type": "http",
"url": "https://api.engram.tools/mcp"
}
}
}{
"context_servers": {
"engram": {
"url": "https://api.engram.tools/mcp"
}
}
}{
"mcpServers": {
"engram": {
"serverUrl": "https://api.engram.tools/mcp"
}
}
}{
"mcpServers": {
"engram": {
"url": "https://api.engram.tools/mcp"
}
}
}name: Engram
version: 0.0.1
schema: v1
mcpServers:
- name: Engram
type: streamable-http
url: https://api.engram.tools/mcp{
"mcpServers": {
"engram": {
"httpUrl": "https://api.engram.tools/mcp"
}
}
}{
"mcpServers": {
"engram": {
"type": "http",
"url": "https://api.engram.tools/mcp"
}
}
}{
"mcpServers": {
"engram": {
"url": "https://api.engram.tools/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.engram.tools%2Fmcp&type=streamable_http&id=engram&name=Engram
It answered our last check on 7 November 2026 in 231 ms. Over 4 checks since 23 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by engram.tools and served from api.engram.tools, the vendor's own domain: https://api.engram.tools/mcp.
17, as returned by the server's own tools/list on 13 November 2026: engram_close_session, engram_cross_pollinate, engram_delete_memory, engram_get_context, engram_list_sessions, engram_proof, engram_recall, engram_reflect, and 9 more.
It answered our last check on 7 November 2026 in 231 ms. Over 4 checks since 23 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.engram.tools/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: tools.engram. Endpoint host: api.engram.tools. ARD identifier: urn:air:tools.engram:mcp:engram.
First indexed 23 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.