ToolTrust
A4/100
xerj-org

xerj

mcp1.0.0-rc.99

@xerj-org

Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid search, code search without grep, agent memory and RAG. Elasticsearch-compatible API; Corpus Hub serves hundreds of reference memory corpora.

By xerj-org | 63 findings | Scanned 10/26/2026 | tooltrust-scanner/v0.3.20 | 15.6k

Repository health

Popularity and maintenance signals alongside the security grade.

View repository
Stars

15.6k

current snapshot

Forks

1.1k

current snapshot

Contributors

81

public GitHub contributors

Last commit

Oct 26, 2026

GitHub repository activity

Last release

Oct 24, 2026

xerj v1.0.0-rc.99

Release version

v1.0.0-rc.99

Latest GitHub release

Stars trend

Daily star additions · History data pending

—

No observed star events yet.

——

Pull request activity

Weekly PR events · History data pending

No observed PR events yet.

——
RustApache-2.0OtherLast scan Oct 26, 2026
12 Low51 Info

Risk Summary

Safe With Normal Controls

Excessive Permissions is the main signal, but overall risk remains within an acceptable range.

Potential impact: The agent may gain overly broad access to files, network, databases, or execution capabilities.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (63)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×11

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    xerj_batch_searchxerj_searchxerj_semantic_searchxerj_vector_searchxerj_hybrid_searchxerj_code_searchxerj_field_reportxerj_corpus_feedbackxerj_hub_findxerj_hub_defxerj_hub_ask

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • LowAS-002

    ⚠️Excessive Permissions

    xerj_corpus_feedback:input schema exposes 12 properties (threshold: 10)

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-002

    ⚠️Excessive Permissions ×21

    declared capabilities: filesystem access, database access

    xerj_defxerj_brain_egoxerj_map

    declared capabilities: network access, filesystem access, database access

    xerj_batch_searchxerj_search

    declared capabilities: network access, database access

    xerj_semantic_searchxerj_hybrid_searchxerj_corpus_feedbackxerj_hub_find

    declared capabilities: network access, database access, HTTP requests

    xerj_vector_search

    declared capabilities: database access

    xerj_memory_recallxerj_brain_linkxerj_brain_unlinkxerj_brain_overviewxerj_plan

    declared capabilities: filesystem access

    xerj_index_budgetxerj_autoindex_remove

    declared capabilities: network access, filesystem access, HTTP requests

    xerj_code_search

    declared capabilities: network access, filesystem access

    xerj_field_reportxerj_hub_defxerj_hub_ask

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

  • InfoAS-010

    🔑Insecure Secret Handling ×8

    input parameter "max_tokens" accepts a credential (informational; not evidence of insecure handling)

    xerj_defxerj_batch_searchxerj_searchxerj_semantic_searchxerj_vector_searchxerj_hybrid_searchxerj_code_searchxerj_hub_ask

    Fix: Avoid accepting raw credentials as input parameters. Use secret managers (e.g. 1Password CLI, AWS Secrets Manager) and ensure credentials are never logged or stored in agent traces.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×22

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    xerj_defxerj_batch_searchxerj_searchxerj_semantic_searchxerj_vector_searchxerj_hybrid_searchxerj_memory_storexerj_memory_recallxerj_brain_egoxerj_brain_linkxerj_brain_unlinkxerj_brain_overviewxerj_mapxerj_index_budgetxerj_autoindex_removexerj_code_searchxerj_planxerj_field_reportxerj_corpus_feedbackxerj_hub_findxerj_hub_defxerj_hub_ask

    Fix: Review and remediate the identified issue.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y xerj"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)