Aggrete MCP server
io.github.Aggrete/aggrete·v0.8.3·1 starsMCP policy proxy: enforces a code of conduct across connectors before the upstream is called.
1 stars663 downloads/wk
Reviews
Write oneNobody has reviewed Aggrete yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Aggrete tools (7)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
budget_rolesBudget lines showing which roles are backfill-only.
foldersDirectory of the available Drive folders and their per-folder tool names.
headcount_planHeadcount plan totals for a team (no individuals).
leave_balanceLeave and absence balances for one person.
oncall_draftDraft on-call rotation for a quarter.
recent_joinersPeople who joined a team within N months.
statusWhy no Drive folders are available yet.
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- Code scan29 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 0 days ago15/15
- Maintainer identityregistry namespace matches repository owner7/10
How Aggrete compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 91/100
- higher than 85% of 48,243 servers
- Tools
- 7
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,706 servers
- Downloads a week
- 663
- more than 91% of 12,306 servers with a package
What its tools let an agent do: 7 read
Install Aggrete in Claude Code, Cursor or VS Code
claude mcp add aggrete -- uvx aggrete
What the publisher says
From the Aggrete repository's README, as published. We do not edit it. Read it on GitHub
Aggrete
An MCP proxy that enforces a code-of-conduct document across connectors, with per-user memory that accumulates across calls.
Four individually-authorized questions can assemble a layoff list — no single one is sensitive, so no guardrail fires. Aggrete is the layer that catches the combination: is this call, together with everything this person already pulled today, something the code of conduct forbids?
Try it live — nothing to install · or uvx aggrete --demo
Install
pip install aggrete # or: uv tool install aggrete
uvx aggrete --demo # the walkthrough — no config, auth, or network
aggrete --config proxy.config.yaml # run it for realThe one example
The check tool dry-runs a plan and returns the verdict before anything is fetched:
Plan check: REFUSED.
1. hr__recent_joiners [hr-personnel] -> allowed
2. finance__budget_roles [finance-comp] -> allowed
3. ops__oncall_draft [ops-rota] -> REFUSED COC-HR-004
Personnel, compensation, and operational rosters may not be combined to
derive the planned departure of identifiable individuals.Each call is fine alone. The third completes a forbidden set across three domains that overlap on the same people, so it's denied before the upstream call — the data is never fetched.
What it does
- Refuses before fetching, using a YAML policy and per-user memory across calls and sessions — not single-call authorization.
- Redacts emails, SSNs, cards, and tokens from results before they reach the model; hides walled tools from users who can't call them.
- Shields against prompt injection — any write after a session reads untrusted content is refused — and against tool poisoning, flagging hidden instructions in tool descriptions.
- Holds upstream credentials itself (confused-deputy safe), with optional per-user on-behalf-of access.
- Audits tamper-evidently — every decision is one hash-chained JSON line (aggrete-audit), forwarded to a SIEM or an OpenTelemetry collector, with Prometheus metrics and health endpoints for operations.
- Ask before you act — check previews any sequence, scenarios lists things to try.
- Hold for a human — action: approve pauses a call until the clause owner approves it, from Slack, the terminal, or the console; the approval is a time-limited, audited grant.
Learn more
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Aggrete: common questions
- Is Aggrete MCP server safe?
- Yes, by our scan: it is graded A (91/100). Read the Aggrete safety report
- How do I install Aggrete?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Aggrete need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Aggrete maintained?
- The last commit was 21 days ago (2026-10-15). The latest release is v0.8.3.
- How does Aggrete compare with other MCP servers?
- safety score 91/100 (higher than 85% of 48,243 servers); tools 7 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.