Skip to main content
Glama
tunahanaliozturk

Derbent

by tunahanaliozturk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Go
Local

Related Servers

Alternatives to Derbent

  • AgentGate

    agentkitai
    A
    license
    A
    quality
    A
    maintenance
    Human-in-the-loop approval gateway for agent tool calls: agents request, policies decide, humans approve via Slack/Discord/web — with an OWASP-LLM-Top-10-tagged audit trail. Self-hostable.
    10
    18 npm
    33
    MIT

Related Servers

  • agent-sudo-mcp

    Kisyntra
    A
    license
    A
    quality
    A
    maintenance
    Local zero-trust permission gateway for AI agents. Enforces policy-based tool authorization, human approvals, scoped permissions, and cryptographically verifiable audit logs.
    4
    56 PyPI
    5
    Apache 2.0

  • mcpcut

    RostislavMatov
    A
    license
    Not graded
    quality
    A
    maintenance
    A local proxy in front of any MCP server for developers on Claude Code or Cursor: see every tool call your agent makes, hold the risky ones for your approval, and keep a secret-redacted journal that is tamper-evident with an external anchor.
    1,050 npm
    Apache 2.0

  • Belay

    Jairogelpi
    A
    license
    Not graded
    quality
    B
    maintenance
    Safe, reversible tool execution for AI agents. It sits between an agent and its tool servers, adding contracts, dry-run planning, policy, approvals, saga execution, and rewind.
    MIT

  • agent-chokepoint

    ydarwish1
    A
    license
    Not graded
    quality
    B
    maintenance
    A security checkpoint for AI agents that intercepts and polices tool calls with allow/block/ask verdicts, taint tracking, and audit logging.
    Apache 2.0

  • FusionAL

    JRM-FusionAL
    A
    license
    Not graded
    quality
    B
    maintenance
    Self-hosted MCP governance gateway that aggregates 150+ tools behind policy profiles (strict/balanced/dev) with a per-call audit trail. Python 3.12/FastAPI, Docker-deployable, built for regulated environments that need observability over agent tool calls.
    1
    MIT
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.7/5.0

Scored across 7 tools

Disambiguation5/5

The seven tools split cleanly into two non-overlapping domains (handoffs and memory notes), and within each domain the operations target distinct lifecycle stages. handoff_create/take/list/done are unambiguous, and memory_read (by id) versus memory_search (by query) are clearly differentiated.

Naming Consistency4/5

All names use a predictable snake_case namespace_verb pattern (handoff_*, memory_*), which is easy to scan. The only minor wrinkle is handoff_done, which is a state adjective rather than a verb like the others, but consistency overall is strong.

Tool Count5/5

Seven tools is a well-scoped set for a coordination server: four handoff operations and three memory operations, each earning its place. Nothing is redundant or missing at the count level.

Completeness4/5

Coverage is solid: handoffs support create/list/take/done, and memory supports write/read/search plus supersedes for replacement. Minor gaps remain (e.g., no delete or list-all for memory notes, no cancel/release for a taken handoff), but agents can work around these.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources