Mengram is answering right now. Last checked 13 min ago. Last commit 26 Oct 2026.
Long-term memory for AI agents: semantic facts, episodic events, and procedural workflows
We read the source, 7 h ago · rules 995398eba69f
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
subprocess.run(["pbcopy"], input=post.encode(), check=True)
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.
out = subprocess.run(["git", "-C", str(cwd), *args], capture_output=True, text=True, timeout=timeout)
r = subprocess.run(command, shell=True, capture_output=True, text=True,
const txtFiles = fs.readdirSync(p, { recursive: true })
if (markup) el.innerHTML = markup;
env = dict(os.environ, MENGRAM_PARSE_ONLY="1", MENGRAM_URL="http://127.0.0.1:9")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.
claude mcp add mengram --transport http https://mengram.io/mcp
https://mengram.io/mcp
[mcp_servers.mengram]
url = "https://mengram.io/mcp"
{
"mcpServers": {
"mengram": {
"url": "https://mengram.io/mcp"
}
}
}
{
"servers": {
"mengram": {
"type": "http",
"url": "https://mengram.io/mcp"
}
}
}
This endpoint answered with an authorization challenge. The server is running, and it signs you in through your browser: there is no API key to paste.
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://mengram.io/mcp | streamable-http | sign-in | 327 ms | 13 min ago |
Verification and memory layer for coding-agent workflows.
Value-blind secret metadata and gated workflows for AI coding agents through Phantom's local proxy.
Official Todoist MCP server for AI assistants to manage tasks, projects, and workflows.
MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants
BugBug workflows for AI agents
Orbit's local-first task and workflow registry for coding agents.
Command wrapper MCP server for coding agents, compression, workflows, and local automation.
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
Answers built from our own checks of this server.