Agentguard
Network-egress firewall for agent tools: check URLs against a declarative policy.
Connector by MukundaKatta · GitHub account verified by the MCP Registry
Install
Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.
npx agentmarket install connector/mukundakatta-agentguard
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.
- Tools
- 3 read · 0 write · 0 deleteRead-only
- Secrets
- None asked for
- Install scripts
- Not scanned yet
- Runs as
- Node.js package
Tools by what they do 3
Read from the source code; the running server may list different tools.
Read 3 · Look things up without changing anything.
check_urlcheck_urls_batchvalidate_policy
Tools (3)
Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].
check_urlCheck whether a URL is allowed under a network policy. Returns { allowed, reason } without making any actual request. Use this to gate tool calls before they execute.
check_urls_batchBatch-check multiple URLs against the same policy. Returns per-URL decisions plus an allowed/denied summary. Useful for vetting a list of pending tool fetches.
validate_policySanity-check a policy spec without making any decision. Catches: empty allow list, overly broad "*" wildcards, malformed host patterns containing schemes/paths/queries.
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Weekly downloads
- 18
- Last commit
- Jun 13, 2026 (4 months ago)
- Last release
- Apr 27, 2026 (6 months ago)
- Last package publish
- Apr 27, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026) and the package registry.
Details
- Registry name
io.github.MukundaKatta/agentguard- Version
- 0.1.0
- Auth
- No auth
- Packages
- npm @mukundakatta/agentguard-mcp
- License
- MIT
- Repository
- github.com/MukundaKatta/agentguard-mcp
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
More from MukundaKatta
- 0.489score
Agentcast
MukundaKatta
Structured-output enforcer: extract and validate JSON from messy LLM text.
ConnectorCFreshness: CLocal★ 1↓ 18/wkClaude Code +5 - 0.487score
Agentvet
MukundaKatta
Validate tool-call args before execution.
ConnectorCFreshness: CLocal★ 1↓ 15/wkClaude Code +5 - 0.486score
Agentfit
MukundaKatta
Token-aware message truncation: fit a chat history into your model's context budget.
ConnectorCFreshness: CLocal★ 1↓ 14/wkClaude Code +5 - 0.479score
Ragmetric MCP
MukundaKatta
RAG retrieval IR metrics: recall@k, hit@k, MRR, NDCG@k, evaluate_batch.
ConnectorCFreshness: CLocal↓ 23/wkClaude Code +5 - 0.477score
Agentsnap
MukundaKatta
Snapshot tests for AI tool-call traces: diff, validate, and catch silent regressions.
ConnectorCFreshness: CLocal↓ 20/wkClaude Code +5 - 0.477score
Streamparse
MukundaKatta
Parse partial / truncated / messy JSON for LLM tool calls and structured outputs.
ConnectorCFreshness: CLocalRead-only↓ 20/wkClaude Code +5
Cite this page
Agentguard MCP server. Agent Mart. https://agentmart.dev/connectors/mukundakatta-agentguard (last updated 2026-10-24)