mnemaBLOCK
Signed, append-only decision records for AI coding agents: an MCP server and CLI that open Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, VS Code and Cursor sessions with your team's decisions, hold the edits a rule governs, and let anyone verify the record offline. Tamper-evident, in git.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
Your decisions, handed to your agents' sessions and held at the edits they govern — append-only and signed in the repository, and checkable by anyone.
mnema is a command line and an MCP server that keep the calls behind your AI coding agents' work — decisions, the rules they become, and notes — as signed, append-only facts in the repository. A session in Claude Code, Codex, GitHub Copilot CLI, Gemini CLI, OpenCode, VS Code or Cursor's command-line agent opens with the ones in force, a rule can refuse or pause the write it governs where the host allows, and mnema verify checks the record with no key and no network.
123a152a7695OBSERVED · 2026-10-10Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add vscode --env ACTIONS_ID_TOKEN_REQUEST_TOKEN=${ACTIONS_ID_TOKEN_REQUEST_TOKEN} --env ACTIONS_ID_TOKEN_REQUEST_URL=${ACTIONS_ID_TOKEN_REQUEST_URL} --env MNEMA_KEY_PASSPHRASE=${MNEMA_KEY_PASSPHRASE} -- npx -y @mnema/[email protected]{
"mcpServers": {
"vscode": {
"command": "npx",
"args": [
"-y",
"@mnema/[email protected]"
],
"env": {
"ACTIONS_ID_TOKEN_REQUEST_TOKEN": "${ACTIONS_ID_TOKEN_REQUEST_TOKEN}",
"ACTIONS_ID_TOKEN_REQUEST_URL": "${ACTIONS_ID_TOKEN_REQUEST_URL}",
"MNEMA_KEY_PASSPHRASE": "${MNEMA_KEY_PASSPHRASE}"
}
}
}
}Exposed tools (4)
4 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
a-pattern | read | A pattern. |
cut | read | ${atTheEdge}x |
handoff | read | What to do. |
ok | read | Does a thing. |
Trust audit
BLOCKgrade F · trust 41/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | WARN |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | FAIL |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (5 observation(s))
- Network
- declared (3 observation(s))
- Shell
- declared (2 observation(s))
- Dependencies
- not all pinned
- Secrets in source
- found
Findings (25)
i_string_UTF-16LE_with_BOM.json
i_string_utf16BE_no_BOM.json
i_string_utf16LE_no_BOM.json
n_multidigit_number_then_00.json
n_string_backslash_00.json
'AE9wZW5UaW1lc3RhbXBzAABQcm9vZgC/ieLohOiSlAEI+EOWRicTpf0f79OgQ83bLu2BwA9f6thvBHS/qlUcQuL/8BBe16oQG8Z0zlfaq0z+pgzWCPAIVAI3dmnxCOYI8BBNI+IG57DaDO6Dp2o0vlrUCPAgOcbOL9i6G6KwKZ20NPaB7xC34ZB/6xA5fRxHxrxvcAc
'MIIB+DCCAX6gAwIBAgITNVkDZoCiofPDsy7dfm6geLbuhzAKBggqhkjOPQQDAzAqMRUwEwYDVQQKEwxzaWdzdG9yZS5kZXYxETAPBgNVBAMTCHNpZ3N0b3JlMB4XDTIxMDMwNzAzMjAyOVoXDTMxMDIyMzAzMjAyOVowKjEVMBMGA1UEChMMc2lnc3RvcmUuZGV2MRE
'MIICGjCCAaGgAwIBAgIUALnViVfnU0brJasmRkHrn/UnfaQwCgYIKoZIzj0EAwMwKjEVMBMGA1UEChMMc2lnc3RvcmUuZGV2MREwDwYDVQQDEwhzaWdzdG9yZTAeFw0yMjA0MTMyMDA2MTVaFw0zMTEwMDUxMzU2NThaMDcxFTATBgNVBAoTDHNpZ3N0b3JlLmRldjE
'MIIB9zCCAXygAwIBAgIUALZNAPFdxHPwjeDloDwyYChAO/4wCgYIKoZIzj0EAwMwKjEVMBMGA1UEChMMc2lnc3RvcmUuZGV2MREwDwYDVQQDEwhzaWdzdG9yZTAeFw0yMTEwMDcxMzU2NTlaFw0zMTEwMDUxMzU2NThaMCoxFTATBgNVBAoTDHNpZ3N0b3JlLmRldjE
{}[]
[]
const KEY = 'sk-ant-api03-stand-in-0000000000000000000000000000';
const KEY = 'sk-ant-api03-stand-in-0000000000000000000000000000';
const KEY = 'sk-ant-api03-stand-in-0000000000000000000000000000';
'\n## Considered Options\n\nwe tried sk-ant-api03-ABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789abcdefghijklmnopqrstuvwxyz0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ-abcdefgh\n',
text: 'sk-ant-eater-does-not-eat-any-ants',
const SECRET = 'AKIAABCDEFGHIJKLMNOP';
const SECRET = 'AKIAABCDEFGHIJKLMNOP';
rationale: 'because postgres://u:s3cretpass@h/d',
const PASSWORD_URL = 'postgres://svc:[email protected]/app';
const PASSWORD_URL = 'postgres://svc:[email protected]/app';
'a URL with a user and a password': 'at postgres://svc:[email protected]:5432/app',
Gates applied: no_behavioural_pass.
123a152a7695full audit observations/trust-audit/mcp-server/felipesauer__mnema.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-10 | 123a152a7695 | BLOCK | F | 41 | first audit |
Questions
What is the mnema MCP server?
Signed, append-only decision records for AI coding agents: an MCP server and CLI that open Claude Code, Codex, Copilot CLI, Gemini CLI, OpenCode, VS Code and Cursor sessions with your team's decisions, hold the edits a rule governs, and let anyone verify the record offline. Tamper-evident, in git.
What tools does mnema expose?
4 in total: 4 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is mnema safe to connect to an agent?
No — not without reading the findings first. The audit graded it F (41/100) and found 1 critical or high issue in the source. Each one is listed on this page with the file and line it is on.
What credentials does mnema need?
It reads ACTIONS_ID_TOKEN_REQUEST_TOKEN, ACTIONS_ID_TOKEN_REQUEST_URL and MNEMA_KEY_PASSPHRASE from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does mnema run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as @mnema/vscode at 0.1.0-beta.
How current is this page?
The grade is for one exact copy of the source (123a152a7695), read on 2026-10-10. The repository is watched and re-audited when it changes.