report_agent_issue

SERVERFavCRM SOURCEhttps://api.favcrm.io/mcp

Medium RISK CLASS

Category Write

Parameters 127 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-favcrm-favcrm/report-agent-issue.md

WHAT IT DOES

What report_agent_issue does on FavCRM

AI agents use report_agent_issue to create or update resources in FavCRM, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your FavCRM environment.

Parameter	Type	Required	Description
`area`	string	Yes	Issue area
`logs`	array	—	Relevant error messages, command output, or stack traces
`title`	string	Yes	Short issue title
`severity`	string	Yes	Impact level
`toolCalls`	array	—	Relevant MCP/CLI/SDK calls, arguments, and outcomes
`aiAnalysis`	string	Yes	Agent analysis of likely root cause and impact
`references`	array	—	Source links, file paths, docs, screenshots, or IDs that support the report
`stepsTried`	array	Yes	Concrete steps the agent tried before reporting
`workaround`	string	—	Temporary workaround used, if any
`environment`	object	—	Runtime context such as MCP URL, CLI version, token type, client, sandbox, model, OS
`actualBehavior`	string	Yes	What actually happened
`expectedBehavior`	string	Yes	What the agent or user expected to happen

Parameters from the server's own tool schema.

RISK

Why report_agent_issue is rated Medium

This tool creates a new issue report in the FavCRM system, which is a write operation that generates or modifies data reversibly. It has no destructive effects (data can be edited or deleted), involves no financial transactions, and does not execute arbitrary code or external operations.

From the tool's definition Tool creates a report record with issue details (logs, analysis, references, questions). The description uses language indicating data creation: 'Report... Include...', typical of write operations that generate new support tickets or issue records.

Risk signalsHigh parameter count (13 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs report_agent_issue safely

PolicyLayer is an MCP gateway: it sits between your AI agents and FavCRM, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For report_agent_issue, this is the rule to start with:

report_agent_issue Rate-limited

report_agent_issue stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "report_agent_issue": {
      "limits": [
        {
          "counter": "report_agent_issue_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect FavCRM, apply this rule, and every report_agent_issue call is checked against it from then on.

FAQ

Questions about report_agent_issue

What does the report_agent_issue tool do? +

Report a FavCRM platform issue when an agent finds a missing MCP path, tool failure, confusing schema, CLI/docs issue, or SDK fallback. Include logs, AI analysis, references, and clarification questions so the platform team can follow up. It is categorised as a Write tool in the FavCRM MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does report_agent_issue accept? +

report_agent_issue accepts 12 parameters: area, logs, title, severity, toolCalls, aiAnalysis, references, stepsTried, workaround, environment, actualBehavior, expectedBehavior. Required: area, title, severity, aiAnalysis, stepsTried, actualBehavior, expectedBehavior. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on report_agent_issue? +

Register the FavCRM MCP server in PolicyLayer and add a rule for report_agent_issue: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches FavCRM. Nothing to install.

What risk level is report_agent_issue? +

report_agent_issue is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit report_agent_issue? +

Yes. Add a rate_limit block to the report_agent_issue rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block report_agent_issue completely? +

Set action: deny in the PolicyLayer policy for report_agent_issue. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides report_agent_issue? +

report_agent_issue is provided by the FavCRM MCP server (https://api.favcrm.io/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on FavCRM, and thousands of servers like it.

This server

All 220 FavCRM tools →

Across the catalogue

generate_devtools_report on Percepta MCP Server →generate_forensic_report on Android Forensics ADB MCP Server →team_manager_kill_agent on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →