True Memory Fragments runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 14 Sep 2026.
Detect stale source context and retain traceable code-chain understanding for AI coding agents.
What the code does
We read the source, 20 h ago · rules 3dff92dd89df
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run([sys.executable, str(ORACLE), str(target)], text=True, capture_output=True)
const proc=spawnSync(config.python||"python3",[path.join(integrationRoot,"hooks","pre_tool_use.py")],{input:payload,encoding:"utf8",env});
const current=blobSha(path.join(value.collision.canonical_repo_root,item.path));
proc = subprocess.run(command, input=json.dumps(payload, ensure_ascii=False), shell=True, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, timeout=timeout)
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add true-memory-fragments -- uvx true-memory-fragments{
"mcpServers": {
"true-memory-fragments": {
"args": [
"true-memory-fragments"
],
"command": "uvx"
}
}
}[mcp_servers.true-memory-fragments]
command = "uvx"
args = ["true-memory-fragments"]{
"mcpServers": {
"true-memory-fragments": {
"args": [
"true-memory-fragments"
],
"command": "uvx"
}
}
}{
"mcpServers": {
"true-memory-fragments": {
"args": [
"true-memory-fragments"
],
"command": "uvx"
}
}
}Alternatives to True Memory Fragments
same job, measured the same wayEvidence-traced codebase understanding and security scanning for AI agents over MCP.
Project memory for coding agents: requirements, decisions, code graph and delivery telemetry.
Efficient context management: code search, evidence packs, and memory for coding agents.
Deterministic context selection for AI coding agents. Local memory that compounds across sessions.
Persistent memory for AI coding agents — past bugs, decisions, and your corrections, in your repo.
Memory, docs, and repo context layer for engineering agents.
Git-aware safe file ops for AI agents: delete anything except git-tracked source code.
Local code-memory graph for AI coding agents.
True Memory Fragments — questions
Answers built from our own checks of this server.