WRITE to the Knowledge Base. This tool has TWO modes: MODE 1 — SAVE a new card: Provide content with full Markdown following the ACTIONABLE schema below. MODE 2 — REPORT OUTCOME: Provide kb_id + outcome ('success' or 'failure'). WHEN TO USE: - Mode 1: After successfully fixing a bug IF no existin...
Risk signalsAccepts raw HTML/template content (content) · Admin/system-level operation
Part of the Fixflow server.
Free to start. No card required.
AI agents use save_kb_card to create or modify resources in Fixflow. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call save_kb_card repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Fixflow.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"save_kb_card": {
"limits": [
{
"counter": "save_kb_card_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Fixflow policy for all 3 tools.
These attack patterns abuse exactly the kind of access save_kb_card gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
WRITE to the Knowledge Base. This tool has TWO modes: MODE 1 — SAVE a new card: Provide content with full Markdown following the ACTIONABLE schema below. MODE 2 — REPORT OUTCOME: Provide kb_id + outcome ('success' or 'failure'). WHEN TO USE: - Mode 1: After successfully fixing a bug IF no existing KB card covered it. - Mode 2: ALWAYS after applying a solution from read_kb_doc and running verification. INPUT: - content: (Mode 1) Full Markdown KB card content — follow the EXACT template below. - overwrite: (Mode 1) Set to True to update an existing card. - kb_id: (Mode 2) ID of the card to report outcome for. - outcome: (Mode 2) 'success' or 'failure'. - enrichment: (Mode 2, optional) Additional context to merge into the card when outcome is 'failure'. ━━━ CARD TEMPLATE (Mode 1) — copy this structure EXACTLY ━━━ --- kb_id: "[PLATFORM]_[CATEGORY]_[NUMBER]" # e.g. WIN_TERM_001, CROSS_DOCKER_002 title: "[Short Title — max 5 words]" category: "[terminal|devops|supabase|fastmcp|network|database|...]" platform: "[windows|linux|macos|cross-platform]" technologies: [tech1, tech2] complexity: [1-10] criticality: "[low|medium|high|critical]" created: "[YYYY-MM-DD]" tags: [tag1, tag2, tag3] related_kb: [] --- [Short Title — max 5 words] > TL;DR: [One sentence — what's the problem + solution] > Fix Time: ~[X min] | Platform: [Windows/Linux/macOS/All] --- 🔍 This Is Your Problem If: - [ ] [Symptom 1 — specific symptom or error message] - [ ] [Symptom 2 — specific error code or log line] - [ ] [Symptom 3 — environment/version condition] Where to Check: [console / logs / env / task manager / etc.] --- ✅ SOLUTION (copy-paste) 🎯 Integration Pattern: [Global Scope] / [Inside Init] / [Event Handler] [language] [One-line comment — what this code does] [depersonalized code WITHOUT specific paths, use __VAR__ for things to replace] ⚡ Critical (won't work without this): - ✓ [Critical Point 1] — [why it's essential] - ✓ [Critical Point 2] — [common mistake to avoid] 📌 Versions: - Works: [OS/library versions where confirmed working] - Doesn't Work: [OS/library versions where known broken] --- ✔️ Verification (<30 sec) bash [single command to verify the fix worked] Expected: ✓ [Specific output or behavior that confirms success] If it didn't work → see Fallback below ⤵ --- 🔄 Fallback (if main solution failed) Option 1: [approach name] bash [command] When: [condition to use this option] | Risks: [what might break] Option 2: [alternative approach] bash [command] When: [condition] | Risks: [what might break] --- 💡 Context (optional) Root Cause: [1 sentence — why this problem occurs] Side Effects: [what might change after applying the fix] Best Practice: [how to avoid this in future — 1 point] Anti-Pattern: ✗ [what NOT to do — common mistake] --- Applicable: [OS, library versions, conditions] Frequency: [rare / common / very common] ━━━ END OF TEMPLATE ━━━ RULES for ACTIONABLE cards: 1. Solution FIRST — after diagnosis, code immediately 2. Depersonalize — no names, project names, or absolute paths 3. Use __VAR__ markers for anything the user must replace 4. One Verification command, result visible in <30 sec 5. Fallback — 1-2 options max, always include When/Risks 6. Context at End — WHY is optional reading for curious agents. It is categorised as a Write tool in the Fixflow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Fixflow MCP server in PolicyLayer and add a rule for save_kb_card: 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 Fixflow. Nothing to install.
save_kb_card is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the save_kb_card 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.
Set action: deny in the PolicyLayer policy for save_kb_card. 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.
save_kb_card is provided by the Fixflow MCP server (https://fixflow-mcp.onrender.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 Fixflow tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.