chakoshi MCP Serverofficial
A
licenseB
qualityD
maintenanceEnables MCP clients to check text content using chakoshi's guardrail API for safety and moderation, returning assessment results.
1
3
MIT
loopquest-mcp
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@loopquest-mcpCreate a review task for this email draft."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
loopquest-mcp
A Model Context Protocol server for LoopQuest. Lets any MCP-capable agent (Claude Desktop, Cursor, Windsurf, custom agents) send its output for gamified human-in-the-loop review and get a verdict back.
Tools
create_review_task — send content for a human to approve or flag. Returns a task id; the verdict arrives via webhook (
callback_url) orget_task_status.get_task_status — check a task's status / verdict.
Related MCP server: Datashift MCP Server
Configure
Set LOOPQUEST_API_KEY (Workspaces → API keys). Optionally LOOPQUEST_BASE_URL for a self-hosted deployment.
Claude Desktop
In claude_desktop_config.json:
{
"mcpServers": {
"loopquest": {
"command": "npx",
"args": ["-y", "loopquest-mcp"],
"env": { "LOOPQUEST_API_KEY": "lq_your_key" }
}
}
}Cursor / Windsurf use the same command / args / env shape in their MCP settings.
Develop
npm install
npm test # unit tests
npm run build # tsc -> dist/
node dist/index.jsLicense
MIT
Available Tools
2 toolscreate_review_taskA
Send content to LoopQuest for a human to review. Use mode=gate to BLOCK until a human approves (poll get_task_status for the verdict before acting), or mode=monitor to review in the background. Returns the task id, status and expiry.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | gate blocks until a human approves; monitor reviews without blocking (default monitor). | |
| claim | No | Grounding: the claim/answer to verify against the source. | |
| title | No | Short title shown on the review card. | |
| module | No | Which review game (default swiper). swiper=approve/flag, versus=pick better of two, sorter=classify, detective=find the error, fixer=confirm/correct fields, redact=mask PII/secrets, grounding=check a claim against its source. | |
| source | No | A label for the originating agent/workflow, shown as a coloured tag. | |
| choices | No | Sorter: the bucket options to classify into. | |
| content | No | The output to review (Swiper, Detective, Redact; the claim for Grounding if 'claim' is empty). | |
| on_timeout | No | Gate: action if the timeout passes with no verdict (default escalate, fail-closed). | |
| external_id | No | Correlation id echoed back in the verdict webhook. | |
| source_text | No | Grounding: the source/context the claim must be supported by. | |
| callback_url | No | Where LoopQuest POSTs the signed verdict. | |
| timeout_seconds | No | Gate: apply the fail-closed default if no human decides within this many seconds. | |
| reviews_required | No | How many reviewers must agree. |
TDQS
A3.9/5.0
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavior. It mentions that gate mode blocks until human approval and that polling get_task_status is required. It also states the return fields. However, it does not discuss authentication requirements, rate limits, data persistence, or what happens on failure (e.g., if the human never reviews). These gaps reduce transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences: first states the primary purpose, second explains the two modes and their usage, third lists return values. It is front-loaded, concise, and contains no redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (13 parameters, conditional logic for modules) and no output schema, the description provides a high-level overview but lacks details on conditional parameter usage (e.g., when 'choices' is required), possible return status values, callback behavior, and error scenarios. It is adequate but not comprehensive.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds some semantic value by explaining the modes and the relationship between 'claim' and 'content' for grounding, but most parameter meanings are already fully covered in the schema descriptions. No significant additional insight is provided beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Send content to LoopQuest for a human to review.' It distinguishes two modes (gate and monitor) and specifies the return values (task id, status, expiry), making the purpose specific and actionable.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains when to use each mode: gate for blocking until human approval (with polling via get_task_status), and monitor for background review. It implicitly guides the agent away from using this tool if polling is not intended, and the sibling tool get_task_status is mentioned in context. However, it does not explicitly state when not to use this tool or discuss alternatives for other review flows.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
get_task_statusA
Check the status and verdict of a LoopQuest review task by id.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task_id | Yes | The task id returned by create_review_task. |
TDQS
A4.5/5.0
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided; the description discloses the tool performs a read operation ('check') to retrieve status and verdict. It is transparent about its non-destructive nature, though it does not detail other behavioral traits such as idempotency or rate limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It is front-loaded and directly addresses the tool's purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one required parameter, no output schema, 100% schema coverage), the description is complete. It provides sufficient information for an agent to select and invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with a clear description for the single parameter. The description adds meaning by specifying 'status and verdict' beyond the schema's 'task id' description, clarifying what is checked.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool checks status and verdict of a review task by id, using the specific verb 'check' and resource 'status and verdict'. It implicitly distinguishes from sibling 'create_review_task' which creates tasks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after creating a task (referenced in parameter description) but does not explicitly state when to use or not use this tool versus alternatives. The context is clear for a simple status check.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
A4.2/5.0
Disambiguation5/5
Each tool has a clearly distinct purpose: one creates a review task, the other checks its status. No overlap or ambiguity.
Naming Consistency5/5
Both tool names follow a consistent verb_noun pattern in snake_case: create_review_task and get_task_status.
Tool Count4/5
With only 2 tools, the server is lightly scoped but still covers the core review workflow. The count is slightly low but acceptable for a focused utility.
Completeness3/5
The tool surface covers creation and status polling, but lacks operations like canceling or listing tasks, which could be needed in real workflows.
Maintenance
ActivityStale
ResponsivenessSyncing
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Human-in-the-loop review and approval for AI agents. Audit trail, approval policies, native MCP.
Human-in-the-loop for AI agents over MCP: durable approvals with a hosted review page & audit trail
Get a real human to verify, decide, or improve an AI agent's work.
A paid remote MCP for HyperFrames, built to return verdicts, receipts, usage logs, and audit-ready J
Related MCP Servers
Datashift MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceEnables AI agents to submit tasks for human or AI review and receive decisions via MCP tools, adding human review checkpoints to workflows.MIT- AlicenseDqualityFmaintenanceEnables AI assistants to request human input by creating tasks on Amazon Mechanical Turk, integrating human-in-the-loop capabilities via the MCP standard.22526ISC
mcp-reviewofficial
AlicenseNot gradedqualityAmaintenanceAn MCP server for in-loop design review of web previews. It enables agents to submit a preview URL, receive structured findings with suggested fixes, and recheck after applying changes, while never editing code itself.1MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/TomPhillipsLabs/loopquest-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server