Skip to main content
hc
Submit
mcpSource-backed

Engram MCP Server

Local-first persistent memory MCP server for AI coding agents, backed by a single Go binary, SQLite, FTS5 search, CLI, HTTP API, and TUI.

by Gentleman Programming · submitted by oktofeesh1·added 2026-06-05·
Claude CodeCodexCursorClaude Desktop
HarnessClaude CodeCodexCursorClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Canonical URL
https://heyclau.de/entry/mcp/engram-mcp-server
Source URLs
https://github.com/Gentleman-Programming/engram/blob/main/docs/AGENT-SETUP.md, https://github.com/Gentleman-Programming/engram
Brand
Engram
Safety notes
Engram can save, update, delete, search, compare, judge, merge, and summarize project memories that may influence future agent behavior., Incorrect or stale memories can steer an agent toward bad assumptions, so review saved decisions, architecture notes, and task learnings periodically., Use explicit project selection or repo-local configuration when multiple projects are visible to the MCP server., Cloud sync is opt-in; review project scope, tokens, allowed projects, and repair flows before enabling shared replication.
Privacy notes
Memories can contain product plans, architecture decisions, code paths, prompts, implementation notes, incident details, and sensitive lessons learned., Local SQLite storage, exported sync chunks, Git-tracked memory files, cloud replication, HTTP API logs, and TUI copy actions can expose memory content., Do not store secrets, credentials, customer data, or unreleased security details unless the local store and any sync targets are approved for that data.
Author
Gentleman Programming
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

63

Baseline

—

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Needs review

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done

  • Source provenance statusRequired

    Marked as source-backed.

    Done

  • Metadata reviewed

    No reviewed flag detected in metadata.

    Pending

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done

  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done

  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done

  • Package verification flag

    No package verification flag provided.

    Pending

  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending

  • Baseline comparison available

    No baseline peer selected yet.

    Pending

  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

10 minutes

Install command

Provided

Config snippet

Provided

Copy snippet

Provided

Prerequisites

4 to clear

Platforms

4 listed

Install type

CLI install

Adoption plan

Balanced adoption plan

Current risk score 24/100. Use staged verification before broader rollout.

Risk 24

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done

  • Confirm metadata review state

    No review metadata found; increase manual validation.

    Pending

  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done

  • Review privacy notesRequired

    Privacy notes are present.

    Done

  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending

  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending

  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Missing required evidence: Metadata review. Risk score 31.

Risk 31

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Missing

Review metadata is missing.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required gaps: Metadata review

Decision timeline

Decision timeline · balanced

Blocking gaps: Check metadata review status. Risk 28.

Risk 28

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is missing.

Pending

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

Blockers: Check metadata review status

Prerequisite readiness

Prerequisite readiness

4 prerequisites to line up before setup. Have accounts and credentials ready first.

0/4 ready
Account & credentials1Install & runtime2Configuration110 minutes

Safety & privacy surface

Safety & privacy surface

4 safety and 3 privacy notes across 4 risk areas. Review closely: credentials & tokens, network access.

4 areas
  • SafetyGeneralEngram can save, update, delete, search, compare, judge, merge, and summarize project memories that may influence future agent behavior.
  • SafetyGeneralIncorrect or stale memories can steer an agent toward bad assumptions, so review saved decisions, architecture notes, and task learnings periodically.
  • SafetyGeneralUse explicit project selection or repo-local configuration when multiple projects are visible to the MCP server.
  • SafetyCredentials & tokensCloud sync is opt-in; review project scope, tokens, allowed projects, and repair flows before enabling shared replication.
  • PrivacyLocal filesMemories can contain product plans, architecture decisions, code paths, prompts, implementation notes, incident details, and sensitive lessons learned.
  • PrivacyNetwork accessLocal SQLite storage, exported sync chunks, Git-tracked memory files, cloud replication, HTTP API logs, and TUI copy actions can expose memory content.
  • PrivacyCredentials & tokensDo not store secrets, credentials, customer data, or unreleased security details unless the local store and any sync targets are approved for that data.

Safety notes

  • Engram can save, update, delete, search, compare, judge, merge, and summarize project memories that may influence future agent behavior.
  • Incorrect or stale memories can steer an agent toward bad assumptions, so review saved decisions, architecture notes, and task learnings periodically.
  • Use explicit project selection or repo-local configuration when multiple projects are visible to the MCP server.
  • Cloud sync is opt-in; review project scope, tokens, allowed projects, and repair flows before enabling shared replication.

Privacy notes

  • Memories can contain product plans, architecture decisions, code paths, prompts, implementation notes, incident details, and sensitive lessons learned.
  • Local SQLite storage, exported sync chunks, Git-tracked memory files, cloud replication, HTTP API logs, and TUI copy actions can expose memory content.
  • Do not store secrets, credentials, customer data, or unreleased security details unless the local store and any sync targets are approved for that data.

Prerequisites

  • Engram binary installed through Homebrew, GitHub Releases, Go install, or a source build.
  • MCP-compatible coding agent such as Claude Code, Codex, OpenCode, Gemini CLI, VS Code, Cursor, or Windsurf.
  • Project selection rules for where memories should be written, especially in monorepos or parent workspaces.
  • Optional cloud server configuration only when shared or cross-machine memory replication is desired.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
10 minutes
Difficulty
intermediate
Full copyable content
{
  "mcpServers": {
    "engram": {
      "command": "engram",
      "args": ["mcp"]
    }
  }
}

About this resource

Content

Engram MCP Server gives AI coding agents persistent project memory through a local-first Go binary backed by SQLite and FTS5 search. It exposes memory tools over MCP stdio while also offering CLI, HTTP API, sync, and TUI interfaces for manual inspection and maintenance.

The upstream README describes Engram as agent-agnostic and compatible with MCP clients including Claude Code, Codex, OpenCode, Gemini CLI, VS Code, Cursor, and Windsurf. The core MCP path is engram mcp; setup helpers are available for several agents.

Source Review

These sources were reviewed on 2026-06-05. Prefer the live installation and agent setup docs for current binary distribution, setup helpers, MCP tool modes, project detection, and cloud sync behavior.

Features

  • Single Go binary with no Node, Python, or Docker runtime dependency for local MCP usage.
  • Local SQLite and FTS5-backed memory search.
  • MCP tools for saving, updating, deleting, searching, contextualizing, summarizing, judging, comparing, and merging memories.
  • Session lifecycle helpers for start, end, and summary workflows.
  • Project detection and explicit project selection rules.
  • TUI for inspecting and searching memories outside the agent.
  • Git sync and optional cloud replication for cross-machine or team workflows.
  • Setup helpers for multiple MCP-compatible coding agents.

Installation

After installing the engram binary, configure an MCP client to launch the stdio server:

{
  "mcpServers": {
    "engram": {
      "command": "engram",
      "args": ["mcp"]
    }
  }
}

The upstream docs also provide setup helpers such as engram setup codex, engram setup opencode, and client-specific manual configuration.

Use Cases

  • Preserve architecture decisions and implementation lessons across agent sessions.
  • Recover relevant context after conversation compaction.
  • Search prior work before changing a project again.
  • Share project memories across machines through reviewed sync workflows.
  • Use memory conflict tools to surface contradictory decisions or stale notes.

Safety and Privacy

Persistent memory can be quietly powerful. Review what agents save, prune stale or incorrect entries, and make project selection explicit when the MCP server can see multiple repositories. Bad memories can become bad future instructions.

Memory content may include private architecture, project strategy, prompts, paths, code details, incidents, and customer context. Treat local stores, exported sync chunks, Git sync files, cloud replicas, HTTP API logs, and copied TUI output as sensitive project data.

Duplicate Check

No Gentleman-Programming/engram entry, Engram MCP entry, or matching source URL was found in content/mcp. This is distinct from general memory or notes tools because Engram exposes a coding-agent memory protocol over MCP with local SQLite search and optional sync.

#memory#coding-agents#sqlite#local-first#search

Source citations

Add this badge to your README

Show that Engram MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/mcp/engram-mcp-server.svg)](https://heyclau.de/entry/mcp/engram-mcp-server)

How it compares

Engram MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

1 trust signal differ across this comparison (Submitter).

Field
Engram MCP Server

Local-first persistent memory MCP server for AI coding agents, backed by a single Go binary, SQLite, FTS5 search, CLI, HTTP API, and TUI.

Open dossier
GoodMemory MCP Server

Local-first GoodMemory MCP server for giving Claude durable, scoped memory with SQLite storage, auditable recall, explicit deletion, and opt-in governed writes.

Open dossier
ChunkHound logoChunkHound MCP Server

Local-first codebase intelligence MCP server that indexes repositories with tree-sitter, stores searchable chunks in DuckDB, and gives Claude semantic search, regex search, daemon status, and deep code research tools.

Open dossier
Roam Code logoRoam Code

Local codebase intelligence CLI and MCP server that gives Claude a SQLite code graph, change-safety gates, code health checks, impact analysis, review tools, and audit evidence for agent-assisted coding.

Open dossier
Next steps
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Open dossierAPI JSONOpen LLMMCP feedOpen sourceNewsletterClaim listing
Trust
Review statusNot reviewedNot reviewedNot reviewedNot reviewed
Package trustPackage not verifiedPackage not verifiedPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backedSource-backedSource-backed
SubmitterDiffersoktofeesh1hjqcanoktofeesh1oktofeesh1
Install riskReview firstReview firstReview firstReview first
Notes Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓ Safety ✓ Privacy ✓
Brand——ChunkHound logoChunkHoundRoam Code logoRoam Code
Categorymcpmcpmcpmcp
SourceSource-backedSource-backedSource-backedSource-backed
AuthorGentleman ProgramminghjqcanChunkHoundCranot
Added2026-06-052026-07-132026-06-062026-06-06
Platforms
Claude CodeCodexCursorClaude Desktop
CodexClaude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Harness
Claude CodeCodexCursorClaude Desktop
CodexClaude CodeClaude Desktop
Claude CodeClaude Desktop
Claude CodeClaude Desktop
Source repo————
Safety notes✓Engram can save, update, delete, search, compare, judge, merge, and summarize project memories that may influence future agent behavior. Incorrect or stale memories can steer an agent toward bad assumptions, so review saved decisions, architecture notes, and task learnings periodically. Use explicit project selection or repo-local configuration when multiple projects are visible to the MCP server. Cloud sync is opt-in; review project scope, tokens, allowed projects, and repair flows before enabling shared replication.✓Standalone MCP starts with eight read-only tools; the governed goodmemory_remember tool is registered only with --allow-write or GOODMEMORY_MCP_ALLOW_WRITE=1. Enabling writes persists selected memory; separate GoodMemory lifecycle APIs can remove stored records, so review write and deletion operations and keep backups of important data. Optional installed-host setup can modify Codex or Claude Code hook and MCP configuration; this is separate from standalone MCP mode.✓ChunkHound reads source files, Markdown, text, PDFs, and supported config files under the target directory and stores indexed chunks in a local database. Realtime indexing and daemon mode can continue watching project files after the initial MCP connection. Code research and web search tools require embedding, reranking, and LLM configuration and may invoke local CLIs or external model APIs depending on settings. Exclude generated files, vendored dependencies, secrets, large artifacts, and unrelated repositories before indexing broad workspace roots. Review MCP client configuration carefully when using an absolute project path in a global Claude Desktop config.✓Roam Code exposes many code-intelligence MCP tools; choose the narrowest `ROAM_MCP_PRESET` needed for the workflow. The server indexes local source code into a `.roam` SQLite-backed graph and may write run ledgers, decision receipts, caches, and generated evidence files. Some workflows can support change planning, review, and higher-authority modes, so keep `ROAM_AGENT_MODE` aligned with the MCP client's approval model. Static analysis, blast-radius, security, and health checks can miss runtime behavior or project-specific constraints. Treat Roam Code output as guidance for review and testing, not as proof that a change is safe to merge.
Privacy notes✓Memories can contain product plans, architecture decisions, code paths, prompts, implementation notes, incident details, and sensitive lessons learned. Local SQLite storage, exported sync chunks, Git-tracked memory files, cloud replication, HTTP API logs, and TUI copy actions can expose memory content. Do not store secrets, credentials, customer data, or unreleased security details unless the local store and any sync targets are approved for that data.✓Standalone mode stores durable memory in local SQLite by default, under the GoodMemory home directory, until the user exports or deletes it. Recalled memory is inserted into Claude's model context and can therefore be sent to the configured model provider. Optional PostgreSQL, embedding, or assisted-extraction providers change the data boundary and may send memory content to configured external services.✓Indexed chunks, file paths, symbols, comments, Markdown, PDFs, configuration values, database files, daemon state, and search results can reveal proprietary source code and internal architecture. Embedding, reranking, LLM, and web search providers may receive code-derived queries or snippets if configured. Local ChunkHound database files, logs, daemon state, and MCP transcripts may retain code-derived context after the session ends. Avoid sharing ChunkHound databases, config files with API keys, verbose logs, research outputs, and screenshots from private repositories.✓Local source paths, symbols, imports, call graphs, git history, dependency relationships, and run evidence can be written to local Roam Code artifacts. The README describes the project as local by default with no API keys required and opt-in summary-only metrics push as the outbound surface. Review `.roam` artifacts, generated evidence, SARIF, reports, and logs before sharing them outside the repository. Avoid indexing private, regulated, or customer code unless the local machine, MCP client, and model workflow are approved for that codebase.
Prerequisites
  • Engram binary installed through Homebrew, GitHub Releases, Go install, or a source build.
  • MCP-compatible coding agent such as Claude Code, Codex, OpenCode, Gemini CLI, VS Code, Cursor, or Windsurf.
  • Project selection rules for where memories should be written, especially in monorepos or parent workspaces.
  • Optional cloud server configuration only when shared or cross-machine memory replication is desired.
  • Bun 1.3 or newer on PATH for the packaged MCP command.
  • Node.js 20 or newer and npm for the global package install.
  • A stable user id to scope recalled and stored memory.
  • A writable local GoodMemory directory, or an explicitly configured PostgreSQL store.
  • Python 3.10 or newer and the `uv` package manager.
  • A local repository or workspace you are authorized to index.
  • ChunkHound JSON config reviewed for database path, excludes, embeddings, and LLM provider settings.
  • Optional embedding provider credentials for semantic search, or regex-only usage when no embedding key is configured.
  • Python 3.10 or newer.
  • A local repository that can be indexed by Roam Code.
  • Permission for the MCP client to read the target codebase and write Roam Code local index and evidence artifacts.
  • Run `roam init` or `roam index` in the repository before expecting complete graph-aware answers.
Install
brew install gentleman-programming/tap/engram
npm install -g goodmemory@0.5.1
uv tool install chunkhound
pip install "roam-code[mcp]"
Config
{
  "mcpServers": {
    "engram": {
      "command": "engram",
      "args": ["mcp"]
    }
  }
}
{
  "mcpServers": {
    "goodmemory": {
      "command": "goodmemory-mcp",
      "args": ["--standalone", "--user-id", "YOUR_USER_ID"]
    }
  }
}
{
  "mcpServers": {
    "chunkhound": {
      "command": "chunkhound",
      "args": ["mcp", "/path/to/approved/project"]
    }
  }
}
{
  "mcpServers": {
    "roam-code": {
      "command": "roam",
      "args": ["mcp"],
      "env": {
        "ROAM_MCP_PRESET": "core",
        "ROAM_AGENT_MODE": "read_only"
      }
    }
  }
}
Citations
ClaimUnclaimedUnclaimedUnclaimedUnclaimed
Open 4 picks in the interactive comparison tool

Related guides

Source-backed guides for putting this to work.

Troubleshooting High CPU Memory And Search Problems In Claude Code

Fix Claude Code CPU, memory, and search issues with /compact, /heapdump, and ripgrep steps from official docs.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Compaction and Memory Hygiene for Long Claude Sessions

Use /compact, /memory, and CLAUDE.md hygiene to keep long Claude Code sessions accurate.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by kiannidev

Build a Local-First AI Developer Stack

Run AI dev tools, MCP servers, models, and memory on infrastructure you own.

Added 1mo ago
guidesReview firstSource-backedReview first
Safety ✓ Privacy ✓by dpdanpittman

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.