io.github.meharajM/agent-loop-mcp
NPM · @MHRJ/MCP-AGENT-LOOP · SCANNED SEP 22
Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp
Available components
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 → Why this is hard to score →
Supply Chain Security97
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 43 of 109 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (ISC).Pass
- Actively maintained (last published 190 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability83
- 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 Management100
- No destabilizing schema changes in the last 30 days.Pass
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
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "resume_loop" implies "remove" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the io.github.meharajM/agent-loop-mcp server?
io.github.meharajM/agent-loop-mcp runs locally as an npm package, launched with npx -y @mhrj/mcp-agent-loop. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @mhrj/mcp-agent-loop
claude mcp add meharajm-agent-loop-mcp -- npx -y @mhrj/mcp-agent-loop
{
"mcpServers": {
"meharajm-agent-loop-mcp": {
"command": "npx",
"args": [
"-y",
"@mhrj/mcp-agent-loop"
]
}
}
} {
"servers": {
"meharajm-agent-loop-mcp": {
"command": "npx",
"args": [
"-y",
"@mhrj/mcp-agent-loop"
]
}
}
} codex mcp add meharajm-agent-loop-mcp -- npx -y @mhrj/mcp-agent-loop
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"meharajm-agent-loop-mcp": {
"type": "local",
"command": [
"npx",
"-y",
"@mhrj/mcp-agent-loop"
],
"enabled": true
}
}
} openclaw mcp add meharajm-agent-loop-mcp --command npx --arg -y --arg @mhrj/mcp-agent-loop
mcp_servers:
meharajm-agent-loop-mcp:
command: "npx"
args: ["-y", "@mhrj/mcp-agent-loop"] {
"McpServers": {
"meharajm-agent-loop-mcp": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@mhrj/mcp-agent-loop"
]
}
}
} assistant mcp add meharajm-agent-loop-mcp -t stdio -c npx -a -y @mhrj/mcp-agent-loop
{
"mcpServers": {
"meharajm-agent-loop-mcp": {
"command": "npx",
"args": [
"-y",
"@mhrj/mcp-agent-loop"
]
}
}
} 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.
- 22 Sept 26 +1
- Stability: 0.97 → pass security
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 +1
- Stability: 0.97 → pass security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 −3
- Stability: pass → 0.80 functional
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 22 Sept 2026 · Analysed npm/@mhrj/mcp-agent-loop@1.0.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 109 packages
| Packages resolved | 109 |
|---|---|
| Stale | 43 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
compact_memory ~59
Empties the Active Context and appends the AI-provided summary to the Compacted History.
| Name | Type | Req | Description |
|---|---|---|---|
| context_summary | string | yes | A highly condensed summary of the current Active Context to preserve important facts and outcomes. |
| session_id | string | yes | – |
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.
| Name | Type | Req | Description |
|---|---|---|---|
| objective | string | yes | The overarching objective for the agent to achieve |
| session_id | string | yes | A 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.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | A short description of what was just done |
| failed | boolean | yes | Set to true if this step encountered an error or failed to achieve its micro-goal. |
| result | string | yes | The output, success, or failure message of the action |
| self_heal_strategy | string | – | MANDATORY if failed=true. How you plan to fix this failure or what alternative tool you will explore next. |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
report_blocker ~49
Updates state to STATUS_BLOCKED and asks for human intervention when absolutely stuck.
| Name | Type | Req | Description |
|---|---|---|---|
| reason | string | yes | The reason the loop is blocked and needs human help |
| session_id | string | yes | – |
No output schema declared.
No examples provided.
resume_loop ~45
Removes the block and adds human input context back into the loop.
| Name | Type | Req | Description |
|---|---|---|---|
| session_id | string | yes | – |
| user_input | string | yes | The clarify or credentials provided by the human |
No output schema declared.
No examples provided.
What is the io.github.meharajM/agent-loop-mcp server?
io.github.meharajM/agent-loop-mcp is listed in the public MCP registry as io.github.meharajM/agent-loop-mcp. Agentic memory manager. Install Skill: npx skills add meharajM/agent-loop-mcp. This page covers its npm package (@mhrj/mcp-agent-loop).
Is the io.github.meharajM/agent-loop-mcp server safe to use?
io.github.meharajM/agent-loop-mcp scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the io.github.meharajM/agent-loop-mcp server expose?
io.github.meharajM/agent-loop-mcp exposes 6 tools: init_loop, log_step, compact_memory, report_blocker, resume_loop, get_tool_suggestions. Their descriptions and schemas cost roughly 371 tokens of context every time the server is loaded.
Is the io.github.meharajM/agent-loop-mcp server still maintained?
io.github.meharajM/agent-loop-mcp is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the io.github.meharajM/agent-loop-mcp server under?
io.github.meharajM/agent-loop-mcp declares the ISC licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.