agentRamenSAFE
Local-first codebase intelligence memory and task context for coding agents, via CLI, MCP, and local HTTP.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/palrajjp/agentRamen/actions/workflows/tests.yml) [](https://www.python.org/) [](https://pypi.org/project/agentramen/) [](LICENSE) [](https://github.com/palrajjp/agentRamen/stargazers) [](https://hol.org/registry/plugins/palrajjp%2Fagentramen)
Apache-2.0 licensed. See the security policy and community code of conduct.
[](https://ossdrop.com/tool/agentramen)
agentRamen indexes source structure and Git history, then retrieves task-relevant files and excerpts. It is local-first by default: each developer keeps a private SQLite index. Teams can optionally publish sanitized, commit-pinned snapshots to a centrally hosted, OIDC-protected read-only MCP service.
Quick start
Install agentRamen, then run it from the repository you want to explore:
python -m pip install agentramen cd /path/to/your/repository agentramen init agentramen context "Add authentication" --budget 2000 agentramen impact src/auth.py
agentramen init creates the configuration, i
970f9b1db462OBSERVED · 2026-10-11Connect
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.
claude mcp add agentramen -- None agentramen==0.2.5 mcp
Exposed tools (10)
10 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
repo_architecture | read | return with_provenance(architecture(snapshot_root)) |
repo_context | read | return with_provenance(context_for(snapshot_root, task, token_budget)) |
repo_dependencies | read | return with_provenance({ |
repo_explain | read | return with_provenance(explain_file(snapshot_root, path)) |
repo_graph | read | return with_provenance(graph_export(snapshot_root)) |
repo_hotspots | read | return with_provenance({ |
repo_impact | read | return with_provenance(dependency_impact(snapshot_root, path)) |
repo_search | read | return with_provenance({ |
repo_status | read | return with_provenance( |
repo_team_memory_search | read | return with_provenance({ |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (3)
.codexignore
address = f"http://127.0.0.1:{server.server_port}"Please do not open a public issue for an exploitable vulnerability. Use [GitHub's private vulnerability reporting](https://github.com/palrajjp/agentRamen/security/advisories/new) to contact the mainta
Gates applied: no_behavioural_pass.
970f9b1db462full audit observations/trust-audit/mcp-server/palrajjp__agentramen.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 |
|---|---|---|---|---|---|
| 2026-10-11 | 970f9b1db462 | SAFE | B | 89 | first audit |
Questions
What is the agentRamen MCP server?
Local-first codebase intelligence memory and task context for coding agents, via CLI, MCP, and local HTTP.
What tools does agentRamen expose?
10 in total: 10 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is agentRamen safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does agentRamen need?
No credential environment variables were found in its source, so it appears to need none.
How does agentRamen run?
It speaks stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as agentramen-vscode at 0.1.0.
How current is this page?
The grade is for one exact copy of the source (970f9b1db462), read on 2026-10-11. The repository is watched and re-audited when it changes.