AgentGate
NPM · @AGENTKITAI/AGENTGATE-MCP · SCANNED SEP 21
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
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 Security98
- 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
- 32 of 98 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency84
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to agentkitai/agentgate). View diagnostics → Pass
- License check failed: no license is declared. See how to fix → Fail
- Actively maintained (last published 86 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability75
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 562 tokens (~56/item across 10 items; 10 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
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; "agentgate_delete_policy" implies "delete" 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 10 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 AgentGate MCP server?
AgentGate runs locally as an npm package, launched with npx -y @agentkitai/agentgate-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @agentkitai/agentgate-mcp
claude mcp add agentkitai-agentgate -- npx -y @agentkitai/agentgate-mcp
{
"mcpServers": {
"agentkitai-agentgate": {
"command": "npx",
"args": [
"-y",
"@agentkitai/agentgate-mcp"
]
}
}
} {
"servers": {
"agentkitai-agentgate": {
"command": "npx",
"args": [
"-y",
"@agentkitai/agentgate-mcp"
]
}
}
} codex mcp add agentkitai-agentgate -- npx -y @agentkitai/agentgate-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"agentkitai-agentgate": {
"type": "local",
"command": [
"npx",
"-y",
"@agentkitai/agentgate-mcp"
],
"enabled": true
}
}
} openclaw mcp add agentkitai-agentgate --command npx --arg -y --arg @agentkitai/agentgate-mcp
mcp_servers:
agentkitai-agentgate:
command: "npx"
args: ["-y", "@agentkitai/agentgate-mcp"] {
"McpServers": {
"agentkitai-agentgate": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@agentkitai/agentgate-mcp"
]
}
}
} assistant mcp add agentkitai-agentgate -t stdio -c npx -a -y @agentkitai/agentgate-mcp
{
"mcpServers": {
"agentkitai-agentgate": {
"command": "npx",
"args": [
"-y",
"@agentkitai/agentgate-mcp"
]
}
}
} 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.
- 21 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 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 0
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
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 21 Sept 2026 · Analysed npm/@agentkitai/agentgate-mcp@0.0.3
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | agentkitai/agentgate |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/agentkitai/agentgate/.github/workflows/publish-mcp.yml@refs/tags/mcp-v0.0.3 |
| Rekor log index | 1971372566 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:60e33966971de4977f872d43dbd58dcd0fad48a5259fadc7ce196c53c42d42d3ebd3ede0db08a74e406e990559d6118f14131ec8323d0c8cef0e0f1f7 |
Background: How many MCP packages publish verified provenance →
Dependencies 98 packages
| Packages resolved | 98 |
|---|---|
| Stale | 32 |
| 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 →
agentgate_create_policy ~69
Create a new policy with rules.
| Name | Type | Req | Description |
|---|---|---|---|
| enabled | boolean | – | Whether policy is enabled (default true) |
| name | string | yes | Policy name |
| priority | number | – | Policy priority (default 100) |
| rules | array | yes | Array of policy rules with match conditions and decisions |
No output schema declared.
No examples provided.
agentgate_decide ~77
Approve or deny a pending request. Use when you are the designated approver.
| Name | Type | Req | Description |
|---|---|---|---|
| decidedBy | string | – | Who is making this decision (default: "mcp:user") |
| decision | string | yes | Your decision |
| id | string | yes | Request ID |
| reason | string | – | Reason for decision (optional) |
No output schema declared.
No examples provided.
agentgate_delete_policy ~25
Delete a policy by ID.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Policy ID |
No output schema declared.
No examples provided.
agentgate_get ~29
Get the current status of an approval request by ID.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Request ID |
No output schema declared.
No examples provided.
agentgate_get_audit_actors ~21
Get unique actor values from audit logs.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
agentgate_list ~39
List approval requests with optional filters.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | Max results (default 10) |
| status | string | – | Filter by status |
No output schema declared.
No examples provided.
agentgate_list_audit_logs ~127
List audit log entries with optional filters and pagination.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | – | Filter by action |
| actor | string | – | Filter by actor |
| eventType | string | – | Filter by event type |
| from | string | – | Start date (ISO format) |
| limit | number | – | Max results (default 50, max 100) |
| offset | number | – | Offset for pagination |
| requestId | string | – | Filter by request ID |
| status | string | – | Filter by status |
| to | string | – | End date (ISO format) |
No output schema declared.
No examples provided.
agentgate_list_policies ~18
List all policies ordered by priority.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
agentgate_request ~89
Submit an approval request. Returns request ID and initial status.
| Name | Type | Req | Description |
|---|---|---|---|
| action | string | yes | Action being requested (e.g., "send_email", "make_purchase") |
| context | object | – | Additional context for the approver |
| params | object | – | Action parameters (e.g., { to: "user@example.com", subject: "..." }) |
| urgency | string | – | Request urgency |
No output schema declared.
No examples provided.
agentgate_update_policy ~68
Replace an existing policy (all fields required).
| Name | Type | Req | Description |
|---|---|---|---|
| enabled | boolean | – | Whether policy is enabled |
| id | string | yes | Policy ID |
| name | string | yes | Policy name |
| priority | number | – | Policy priority |
| rules | array | yes | Array of policy rules |
No output schema declared.
No examples provided.
What is the AgentGate MCP server?
AgentGate is an MCP server listed in the public MCP registry as io.github.agentkitai/agentgate. Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve. This page covers its npm package (@agentkitai/agentgate-mcp).
Is the AgentGate MCP server safe to use?
AgentGate scores 90 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 AgentGate MCP server expose?
AgentGate exposes 10 tools: agentgate_request, agentgate_get, agentgate_list, agentgate_decide, agentgate_list_policies, and 5 more. Their descriptions and schemas cost roughly 562 tokens of context every time the server is loaded.
Is the AgentGate MCP server still maintained?
AgentGate is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.