Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.meharajM/agent-loop-mcp

NPM · @MHRJ/MCP-AGENT-LOOP · SCANNED AUG 3

Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp

+17 this week 68 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (108 of 112), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (108 of 112), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability78
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 390 tokens (~55/item across 7 items; 6 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 69% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · @mhrj/mcp-agent-loop

# add to Claude Code
claude mcp add meharajm-agent-loop-mcp -- npx -y @mhrj/mcp-agent-loop
# add to Codex CLI
codex mcp add meharajm-agent-loop-mcp -- npx -y @mhrj/mcp-agent-loop
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "meharajm-agent-loop-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@mhrj/mcp-agent-loop"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add meharajm-agent-loop-mcp --command npx --arg -y --arg @mhrj/mcp-agent-loop
# ~/.hermes/config.yaml
mcp_servers:
  meharajm-agent-loop-mcp:
    command: "npx"
    args: ["-y", "@mhrj/mcp-agent-loop"]
// mcp.json
{
  "mcpServers": {
    "meharajm-agent-loop-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@mhrj/mcp-agent-loop"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +25
    • Provenance: fail → unverified security
    • Install scripts: pass → unverified security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Maintenance: pass → unverified functional
    • License: pass → unverified functional
    • Stability: unverified → 0.20 functional
    • Dependency health: unverified → partial functional
    • Licence: ISC functional
  • 1 Aug 26 +30
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • MCP protocol: unverified → pass functional
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → 100 functional
  • 31 Jul 26 −35
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −31
    • Known CVEs: partial → unverified security
    • Malware scan: pass → unverified security
    • Dependency health: partial → unverified functional
  • 29 Jul 26 +54
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Install scripts: unverified → pass security
    • Schema quality: unverified → good functional
    • Maintenance: unverified → pass functional
    • Schema quality: unverified → 100 functional
    • License: unverified → pass functional
    • Tool coverage: unverified → 100 functional
    • Licence: ISC functional
  • 28 Jul 26 −26
    • Tool coverage: 100 → unverified functional
    • Schema quality: 100 → unverified functional
    • Dependency health: unverified → partial functional
  • 27 Jul 26 51

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/@mhrj/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 108 packages

108 packages in the resolved dependency tree · 108 deprecated · 41 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 6 exposed · ~371 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
compact_memory ~59

Empties the Active Context and appends the AI-provided summary to the Compacted History.

NameTypeReqDescription
context_summarystringyesA highly condensed summary of the current Active Context to preserve important facts and outcomes.
session_idstringyes

No output schema declared.

No examples provided.

get_tool_suggestions ~26

Ask this tool if you are stuck and don't know what other tools to use.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

init_loop ~58

Creates a new .md loop state file for the given session to start a continuous, autonomous task.

NameTypeReqDescription
objectivestringyesThe overarching objective for the agent to achieve
session_idstringyesA unique identifier for this loop session

No output schema declared.

No examples provided.

log_step ~134

Appends to the Active Context. Rejects if failed=true but no self_heal_strategy is provided. Warns if context is too large.

NameTypeReqDescription
actionstringyesA short description of what was just done
failedbooleanyesSet to true if this step encountered an error or failed to achieve its micro-goal.
resultstringyesThe output, success, or failure message of the action
self_heal_strategystringMANDATORY if failed=true. How you plan to fix this failure or what alternative tool you will explore next.
session_idstringyes

No output schema declared.

No examples provided.

report_blocker ~49

Updates state to STATUS_BLOCKED and asks for human intervention when absolutely stuck.

NameTypeReqDescription
reasonstringyesThe reason the loop is blocked and needs human help
session_idstringyes

No output schema declared.

No examples provided.

resume_loop ~45

Removes the block and adds human input context back into the loop.

NameTypeReqDescription
session_idstringyes
user_inputstringyesThe clarify or credentials provided by the human

No output schema declared.

No examples provided.