Mmcp.market

Aletheia Runtime Safety & Scope Creep Filter MCP server

by vikasny30·io.github.vikasny30/aletheia-mcp·v0.3.1

Deterministic pre-execution filter that blocks known scope-creep and prompt-injection tool calls

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

1 stars235 downloads/wk

Reviews

Write one

Nobody has reviewed Aletheia Runtime Safety & Scope Creep Filter yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Aletheia Runtime Safety & Scope Creep Filter tools (6, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • aletheia_get_mandate

    Retrieve the current operational safety mandate, permissions, and active boundary constraints.

  • aletheia_get_telemetry

    Retrieve runtime safety telemetry: total tool calls evaluated, block rate %, latency percentiles (p50, p95, p99 < 1ms), and violation counts broken down by signature.

  • aletheia_intercept

    Universal sub-millisecond safety gatekeeper. Evaluates any proposed tool invocation against Signature S3 (Scope Creep) and S2b (Prompt Injection) to block destructive, out-of-boundary, or compromised actions before execution.

  • aletheia_safe_bashwrite action

    Execute a shell/bash command with inline sub-millisecond Signature S3 scope creep protection. Blocks destructive deletes (rm -rf), disk formatting, fork bombs, credential harvesting, privilege escalation, and unauthorized network egress.

  • aletheia_safe_sql

    Audit or execute a database query with Signature S3 safety filters. Detects destructive DDL (DROP, TRUNCATE), unbounded DML (DELETE/UPDATE without WHERE), and privilege tampering.

  • aletheia_set_mandate

    Establish or update the active operational safety mandate for this agent session. Declares permissible boundaries, allowed tools, filesystem directories, write permissions, and risk tolerance. Loosening restrictions requires operatorSecret.

Public scan report

scanner v0.1.5 · 2026-09-19 · same rubric, same numbers if you re-run it

no findings
  • Code scan27 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 qualitystatic API keys via environment variables6/15
  • Maintenancelast push 6 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

Install directly

Runs npx -y aletheia-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add aletheia-mcp -- npx -y aletheia-mcp
Add to Cursor

Aletheia Runtime Safety & Scope Creep Filter: common questions

Is Aletheia Runtime Safety & Scope Creep Filter MCP server safe?
Mostly: it is graded B (83/100). Read the Aletheia Runtime Safety & Scope Creep Filter safety report
How do I install Aletheia Runtime Safety & Scope Creep Filter?
It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.
Does Aletheia Runtime Safety & Scope Creep Filter need an API key?
Yes. The registry entry asks for ALETHEIA_OPERATOR_SECRET.
Is Aletheia Runtime Safety & Scope Creep Filter maintained?
The last commit was 6 days ago (2026-09-13). The latest release is v0.3.1.
What can I use instead of Aletheia Runtime Safety & Scope Creep Filter?
Servers from other publishers that do the same job: prompt-protection MCP server, mcpm MCP server and MCP Server. Compare all Aletheia Runtime Safety & Scope Creep Filter alternatives.

Alternatives to Aletheia Runtime Safety & Scope Creep Filter

Same job from other publishers: the closest match first, then the best rated.

All Aletheia Runtime Safety & Scope Creep Filter alternatives →
  • prompt-protection
    Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
    A
  • mcpm
    MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
    B
  • MCP Server
    Deterministic intent preflight before your agent builds: six gates, keyless, no model call.
    B
  • MCP
    Authorize consequential AI agent actions before execution
    A
  • Agent-Native Analytics
    Agent-Native Amplitude/Mixpanel - connect data sources, prompt for charts
    A

More from vikasny30