Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

io.github.torkjacobs/tork-governance

NPM · @TORKNETWORK/MCP-SERVER · SCANNED SEP 24

AI agent governance for MCP: PII detection, policy enforcement, compliance, and kill switch.

0 this week 78 Trust /100
Trust breakdown (7 categories)

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
  • 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
  • Repository check failed: the declared repository URL returned HTTP 404. See how to fix → View diagnostics → Fail
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 18 days ago).Pass
  • Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 4387 tokens (~91/item across 48 items; 48 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
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 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "tork_governed_passthrough" implies "execute" 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 48 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
Install

How do I install the io.github.torkjacobs/tork-governance MCP server?

io.github.torkjacobs/tork-governance runs locally as an npm package, launched with npx -y @torknetwork/mcp-server. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @torknetwork/mcp-server

# add to Claude Code
claude mcp add torkjacobs-tork-governance -- npx -y @torknetwork/mcp-server
// .cursor/mcp.json
{
  "mcpServers": {
    "torkjacobs-tork-governance": {
      "command": "npx",
      "args": [
        "-y",
        "@torknetwork/mcp-server"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "torkjacobs-tork-governance": {
      "command": "npx",
      "args": [
        "-y",
        "@torknetwork/mcp-server"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add torkjacobs-tork-governance -- npx -y @torknetwork/mcp-server
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "torkjacobs-tork-governance": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@torknetwork/mcp-server"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add torkjacobs-tork-governance --command npx --arg -y --arg @torknetwork/mcp-server
# ~/.hermes/config.yaml
mcp_servers:
  torkjacobs-tork-governance:
    command: "npx"
    args: ["-y", "@torknetwork/mcp-server"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "torkjacobs-tork-governance": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@torknetwork/mcp-server"
      ]
    }
  }
}
# add to Vellum
assistant mcp add torkjacobs-tork-governance -t stdio -c npx -a -y @torknetwork/mcp-server
// mcp.json
{
  "mcpServers": {
    "torkjacobs-tork-governance": {
      "command": "npx",
      "args": [
        "-y",
        "@torknetwork/mcp-server"
      ]
    }
  }
}
Changelog

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.

  • 24 Sept 26 0
    • Stability: 0.97 → pass security
  • 23 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.

  • 21 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.

  • 19 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.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 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.

  • 14 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.

Diagnostics

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 24 Sept 2026 · Analysed npm/@torknetwork/mcp-server@1.5.1

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 96 packages
Packages resolved 96
Stale 31
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 48 exposed · ~4,387 tokens

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 →

Tool Tokens
tork_approve ~73

Approve a pending HITL request in Tork Cloud. Requires reviewer_id. Requires TORK_API_KEY.

NameTypeReqDescription
approval_idstringyesID of the approval request
commentstring–Optional comment explaining the approval
reviewer_idstringyesID of the human reviewer approving the action

No output schema declared.

No examples provided.

tork_approve_action ~70

Human approves a pending action. Checks for reviewer fatigue and enforces cool-down periods.

NameTypeReqDescription
approval_idstringyesID of the approval request to approve
reasonstring–Optional reason for approval
reviewer_idstringyesID of the human reviewer approving the action

No output schema declared.

No examples provided.

tork_audit_logs ~73

Query audit logs for governance events.

NameTypeReqDescription
agent_idstring–Filter by agent ID
event_typestring–Filter by event type
limitnumber–Maximum number of logs to return (default: 50)
sincestring–ISO timestamp to filter logs after

No output schema declared.

No examples provided.

tork_audit_stats ~48

Get audit statistics for governance events.

NameTypeReqDescription
agent_idstring–Filter by specific agent ID
window_hoursnumber–Time window in hours (default: 24)

No output schema declared.

No examples provided.

tork_check_approval ~43

Check the status of an approval request. Returns current status and whether it has expired.

NameTypeReqDescription
approval_idstringyesID of the approval request to check

No output schema declared.

No examples provided.

tork_check_policy ~88

Check if an action is allowed by the current governance policy without executing it.

NameTypeReqDescription
action_typestringyesType of action (e.g., 'read', 'write', 'delete', 'execute')
agent_idstring–ID of the agent requesting the action
contextobject–Additional context for policy evaluation
resourcestringyesResource being accessed

No output schema declared.

No examples provided.

tork_cloud_audit_logs ~91

Query audit logs from Tork Cloud. Supports filtering by agent, action type, and date. Requires TORK_API_KEY.

NameTypeReqDescription
actionstring–Filter by action type
agent_idstring–Filter by agent ID
limitnumber–Maximum number of logs to return (default: 50)
sincestring–ISO timestamp to filter logs after

No output schema declared.

No examples provided.

tork_cost_alerts ~85

Get unacknowledged cost alerts for an agent. Alerts include budget warnings, threshold breaches, and anomaly detections.

NameTypeReqDescription
agent_idstring–Filter alerts by agent ID (optional)
include_acknowledgedboolean–Include acknowledged alerts (default: false)
limitnumber–Maximum number of alerts to return (default: 20)

No output schema declared.

No examples provided.

tork_cost_budget_status ~46

Check budget status for an agent. Returns all active budgets with current spend, remaining amount, and percent used.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent

No output schema declared.

No examples provided.

tork_cost_check ~81

Check if a proposed spend is allowed before making an API call. Validates against budgets and rate limits. Use this before expensive operations to prevent budget overruns.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
proposed_costnumberyesProposed cost amount in USD
proposed_tokensnumber–Proposed token count (optional)

No output schema declared.

No examples provided.

tork_cost_record ~185

Record a cost transaction for an AI agent. Track LLM calls, embeddings, tool usage, API calls, storage, and compute costs. Essential for budget governance and spend tracking.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
input_tokensnumber–Number of input tokens
metadataobject–Additional metadata about the transaction
modelstring–Model name (e.g., 'gpt-4', 'claude-3-opus')
output_tokensnumber–Number of output tokens
providerstring–Provider name (e.g., 'openai', 'anthropic', 'aws')
session_idstring–Optional session ID for grouping transactions
total_costnumberyesTotal cost of the transaction in USD
transaction_typestringyesType of cost transaction

No output schema declared.

No examples provided.

tork_cost_summary ~59

Get current spend summary for an agent. Shows total cost, transaction count, top providers/models, and budget status.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
periodstring–Summary period (default: daily)

No output schema declared.

No examples provided.

tork_create_webhook ~109

Create a webhook for HITL notifications. Webhooks are called when approvals are requested, approved, or rejected. Requires TORK_API_KEY.

NameTypeReqDescription
event_typesarray–Event types to subscribe to. Options: approval_requested, approval_approved, approval_rejected, approval_timeout. Defaults to ['approval_requested', 'approval_timeout']
namestringyesName for the webhook (e.g., 'Slack Alerts')
urlstringyesURL to receive webhook POST requests

No output schema declared.

No examples provided.

tork_dashboard ~38

Get dashboard statistics from Tork Cloud. Shows total tools, agents, policies, pending approvals, and recent activity. Requires TORK_API_KEY.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tork_delete_webhook ~37

Delete a webhook by ID. Requires TORK_API_KEY.

NameTypeReqDescription
webhook_idstringyesID of the webhook to delete

No output schema declared.

No examples provided.

tork_deny ~75

Deny a pending HITL request in Tork Cloud. Requires reviewer_id and reason. Requires TORK_API_KEY.

NameTypeReqDescription
approval_idstringyesID of the approval request
reasonstringyesReason for denial (required)
reviewer_idstringyesID of the human reviewer denying the action

No output schema declared.

No examples provided.

tork_get_policy ~41

Get a specific governance policy by name from Tork Cloud. Requires TORK_API_KEY.

NameTypeReqDescription
namestringyesName of the policy to retrieve

No output schema declared.

No examples provided.

tork_governance_check ~173

Check if an action is allowed by cloud governance policies. Supports regional PII profiles (v1.1) for country-specific detection. Returns permission status and matched policy. Requires TORK_API_KEY.

NameTypeReqDescription
agent_idstringyesID of the agent requesting the action
industrystring–Industry profile to activate for specialized PII patterns
parametersobject–Parameters being passed to the tool (optional)
regionarray–Regional PII profiles to activate (e.g. ['ae', 'in']). Available: au, us, gb, eu, ae, sa, ng, in, jp, cn, kr, br
targetstring–Target environment or resource (optional)
tool_namestringyesName of the tool being called

No output schema declared.

No examples provided.

tork_governed_passthrough ~169

Execute a tool call with TORK governance checks. Validates parameters, checks policies, scans for PII with optional regional profiles (v1.1), and logs the call.

NameTypeReqDescription
agent_idstring–ID of the agent making the call
correlation_idstring–Optional correlation ID for tracing
industrystring–Industry profile to activate for specialized PII patterns
parametersobjectyesParameters to pass to the tool
regionarray–Regional PII profiles to activate (e.g. ['ae', 'in']). Available: au, us, gb, eu, ae, sa, ng, in, jp, cn, kr, br
tool_namestringyesName of the tool to execute

No output schema declared.

No examples provided.

tork_hitl_check_cooldown ~67

Check if an agent is currently in a cooldown period. Returns cooldown status, type, reason, and remaining time.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
approver_idstring–Optional: Check cooldown for specific approver

No output schema declared.

No examples provided.

tork_hitl_check_velocity ~105

Check velocity limits for an agent/approver. Returns whether additional approvals are allowed based on rate limits. Use before processing approvals to prevent bypass attacks.

NameTypeReqDescription
action_typestring–Type of action being approved (default: 'default')
agent_idstringyesUnique identifier for the agent
approver_idstringyesID of the human approver
valuenumber–Optional value/amount of the action for aggregate tracking

No output schema declared.

No examples provided.

tork_hitl_create_cooldown ~108

Create a cooldown period for an agent. Prevents approvals during the cooldown period. Use when slicing attacks are detected or for manual security lockdowns.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
approver_idstring–Optional: Specific approver to cooldown
cooldown_typestringyesType of cooldown
duration_minutesnumberyesDuration of the cooldown in minutes
reasonstringyesReason for the cooldown

No output schema declared.

No examples provided.

tork_hitl_detect_slicing ~73

Detect slicing attacks - patterns of many small requests that bypass individual review thresholds. Checks for rapid-fire approvals, value aggregation, and pattern anomalies.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent to analyze
approver_idstring–Optional: Analyze patterns for specific approver

No output schema declared.

No examples provided.

tork_hitl_get_config ~50

Get HITL enforcement configuration including velocity limits, cooldown defaults, and slicing detection thresholds.

NameTypeReqDescription
agent_idstring–Optional: Get config for a specific agent (returns agent-specific overrides)

No output schema declared.

No examples provided.

tork_list_approvals ~52

List pending approval requests from Tork Cloud. Filter by status (pending, approved, rejected). Requires TORK_API_KEY.

NameTypeReqDescription
statusstring–Filter by approval status (default: pending)

No output schema declared.

No examples provided.

tork_list_policies ~36

List all governance policies from Tork Cloud. Shows policy names, priorities, and YAML content. Requires TORK_API_KEY.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tork_list_tools ~37

List all registered tools from Tork Cloud. Shows tool configurations, rate limits, and HITL requirements. Requires TORK_API_KEY.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tork_list_webhooks ~26

List all configured webhooks for the organization. Requires TORK_API_KEY.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

tork_mcp_analyze ~97

Run anomaly detection for an agent's MCP tool usage. Checks for high frequency calls, repeated failures, unusual patterns, suspicious parameters, and new tool usage.

NameTypeReqDescription
agent_idstringyesAgent ID to analyze
high_frequency_thresholdnumber–Threshold for high frequency detection (default: 100 calls/minute)
repeated_failure_thresholdnumber–Threshold for repeated failure detection (default: 5 consecutive)

No output schema declared.

No examples provided.

tork_mcp_get_alerts ~119

Get unacknowledged security and anomaly alerts for MCP tool usage. Alerts include high frequency, unusual patterns, repeated failures, and suspicious parameters.

NameTypeReqDescription
agent_idstring–Filter alerts by agent ID (optional)
alert_typestring–Filter by alert type (optional)
include_acknowledgedboolean–Include acknowledged alerts (default: false)
limitnumber–Maximum number of alerts to return (default: 50)
severitystring–Filter by severity level (optional)

No output schema declared.

No examples provided.

tork_mcp_get_stats ~95

Get aggregated statistics for MCP tool usage. Shows total calls, success/failure rates, and average execution times per tool.

NameTypeReqDescription
limitnumber–Maximum number of tool stats to return (default: 100)
order_bystring–Field to order results by (default: total_calls)
tool_namestring–Get stats for a specific tool (optional, returns all if not specified)

No output schema declared.

No examples provided.

tork_mcp_log_call ~159

Log an MCP tool invocation for auditing and compliance. Use this for self-reporting tool calls. Records agent, tool, parameters, result, execution time, and success status.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent making the call
error_messagestring–Error message if the call failed
execution_time_msnumber–Execution time in milliseconds
resultobject–Result returned by the tool
session_idstring–Optional session identifier for grouping related calls
successboolean–Whether the call succeeded (default: true)
tool_namestringyesName of the tool being invoked
tool_parametersobject–Parameters passed to the tool

No output schema declared.

No examples provided.

tork_memory_snapshot ~94

Create a memory fingerprint/snapshot for an agent. Stores a hash of the current memory state for later verification. Use this after significant memory operations to establish a baseline.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
memory_stateobjectyesThe current memory state to snapshot (object or string)
metadataobject–Optional metadata about the snapshot (e.g., session_id, context)

No output schema declared.

No examples provided.

tork_memory_track_modification ~173

Record a memory modification for audit trail. Track all changes to agent memory including adds, updates, deletes, and clears. Essential for compliance and trust scoring.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
authorizedboolean–Whether this modification was authorized (default: true)
authorized_bystring–Who/what authorized the modification
key_pathstring–Path to the modified key (e.g., 'user.preferences.theme')
metadataobject–Additional metadata about the modification
modification_typestringyesType of modification being made
new_valueobject–New value (for adds and updates)
old_valueobject–Previous value (for updates and deletes)
reasonstring–Reason for the modification

No output schema declared.

No examples provided.

tork_memory_trust_score ~170

Get or calculate trust score for an agent based on memory integrity. Trust = (consistency × 0.3) + (compliance × 0.3) + (transparency × 0.2) + (predictability × 0.2). Levels: >0.8 trusted, 0.5-0.8 caution, <0.5 untrusted.

NameTypeReqDescription
actionstring–Action to perform: 'get' retrieves current score, 'calculate' recalculates, 'stats' returns full stats, 'untrusted' lists agents below threshold
agent_idstringyesUnique identifier for the agent
max_trust_levelstring–For 'untrusted' action: maximum trust level to include (default: caution)

No output schema declared.

No examples provided.

tork_memory_verify ~69

Verify current memory against the last snapshot. Detects unauthorized modifications by comparing hashes and identifying changes. Returns drift detection and trust score impact.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
current_memory_stateobjectyesThe current memory state to verify (object or string)

No output schema declared.

No examples provided.

tork_register_tool ~169

Register a tool with a governance policy. Defines which agents can call it, allowed targets, blocked flags, rate limits, and HITL requirements.

NameTypeReqDescription
allowed_agentsarray–List of agent IDs allowed to call this tool. Empty array means all agents allowed.
allowed_targetsarray–List of allowed target environments (e.g., ['dev', 'staging']). Empty means all allowed.
blocked_flagsarray–Additional flags to block beyond defaults (e.g., ['--recursive', '--all'])
max_calls_per_minutenumber–Maximum calls allowed per minute (default: 60)
requires_hitlboolean–Whether this tool requires human-in-the-loop approval
tool_namestringyesUnique name of the tool to register

No output schema declared.

No examples provided.

tork_reject_action ~71

Human rejects a pending action. Does not trigger cool-down as rejections indicate vigilance.

NameTypeReqDescription
approval_idstringyesID of the approval request to reject
reasonstringyesReason for rejection (required)
reviewer_idstringyesID of the human reviewer rejecting the action

No output schema declared.

No examples provided.

tork_request_approval ~117

Submit an action for human approval. Creates an approval request in the queue. Used when a tool requires HITL or for high-risk actions.

NameTypeReqDescription
agent_idstringyesID of the agent requesting approval
amountnumber–Optional monetary amount (for velocity tracking)
parametersstringyesJSON string of parameters for the action
targetstringyesTarget resource or environment (e.g., 'production', 'user@example.com')
tool_namestringyesName of the tool requiring approval

No output schema declared.

No examples provided.

tork_scan_pii ~159

Scan text for PII (Personally Identifiable Information) and optionally redact it. Supports regional PII profiles (v1.1) for country-specific and industry-specific detection across 13 countries and 3 industries. Returns found PII types and redacted text.

NameTypeReqDescription
industrystring–Industry profile to activate for specialized PII patterns
redactboolean–Whether to return redacted text (default: true)
regionarray–Regional PII profiles to activate (e.g. ['ae', 'in']). Available: au, us, gb, eu, ae, sa, ng, in, jp, cn, kr, br
textstringyesThe text to scan for PII

No output schema declared.

No examples provided.

tork_supply_chain_deps ~105

Get dependencies for an AI agent. Returns a list of all registered dependencies or a dependency tree structure showing relationships.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
dependency_typestring–Filter by dependency type (optional)
formatstring–Output format: 'list' for flat list, 'tree' for hierarchical view (default: list)
include_unverifiedboolean–Include unverified dependencies (default: true)

No output schema declared.

No examples provided.

tork_supply_chain_health ~66

Get supply chain health score and report for an agent. Calculates health based on dependency verification status, vulnerability counts, and trust levels.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
include_reportboolean–Include detailed health report (default: true)

No output schema declared.

No examples provided.

tork_supply_chain_register ~165

Register a dependency for an AI agent. Track models, packages, tools, services, APIs, and MCP servers that the agent depends on. Essential for supply chain visibility and health monitoring.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
dependency_typestringyesType of dependency being registered
integrity_hashstring–Integrity hash for verification (optional)
metadataobject–Additional metadata about the dependency
namestringyesName of the dependency (e.g., 'gpt-4', 'lodash', 'stripe-api')
sourcestring–Source registry or provider (e.g., 'npm', 'pypi', 'openai')
versionstring–Version string of the dependency

No output schema declared.

No examples provided.

tork_supply_chain_verify ~96

Verify a dependency against trusted sources. Checks if the source is in the trusted registry and validates the integrity hash if provided.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
dependency_namestringyesName of the dependency to verify
dependency_typestring–Type of dependency (optional, for more specific verification)
expected_hashstring–Expected integrity hash to verify against (optional)

No output schema declared.

No examples provided.

tork_supply_chain_vulns ~80

Check for known vulnerabilities in agent dependencies. Returns vulnerability matches with severity levels and remediation guidance.

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent
include_acknowledgedboolean–Include acknowledged/mitigated vulnerabilities (default: false)
severity_filterstring–Filter by minimum severity level (optional)

No output schema declared.

No examples provided.

tork_tool_call_stats ~64

Get statistics on tool calls including total calls, allowed/blocked counts, and rate limit hits.

NameTypeReqDescription
include_unregisteredboolean–Include stats for unregistered tools (default: false)
tool_namestring–Filter by specific tool name (optional)

No output schema declared.

No examples provided.

tork_validate_tool_call ~112

Validate a tool call BEFORE execution. Checks if tool is registered, agent is allowed, target is allowed, parameters don't contain blocked flags, and rate limits are not exceeded.

NameTypeReqDescription
agent_idstringyesID of the agent making the call
parametersobjectyesParameters that would be passed to the tool
target_environmentstring–Target environment (e.g., 'production', 'staging', 'dev')
tool_namestringyesName of the tool to validate

No output schema declared.

No examples provided.

tork_velocity_alert ~69

Check for slicing attack patterns - detecting many small requests that aggregate to significant impact. Returns velocity stats and alerts.

NameTypeReqDescription
agent_idstring–Agent ID to check velocity for (optional, checks all if not provided)
targetstring–Target/vendor to check velocity for (optional)

No output schema declared.

No examples provided.

Common questions

What is the io.github.torkjacobs/tork-governance MCP server?

io.github.torkjacobs/tork-governance is an MCP server listed in the public MCP registry as io.github.torkjacobs/tork-governance. AI agent governance for MCP: PII detection, policy enforcement, compliance, and kill switch. This page covers its npm package (@torknetwork/mcp-server).

Is the io.github.torkjacobs/tork-governance MCP server safe to use?

io.github.torkjacobs/tork-governance scores 78 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. 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 io.github.torkjacobs/tork-governance MCP server expose?

io.github.torkjacobs/tork-governance exposes 48 tools: tork_scan_pii, tork_governed_passthrough, tork_check_policy, tork_audit_stats, tork_audit_logs, and 43 more. Their descriptions and schemas cost roughly 4,387 tokens of context every time the server is loaded.

Is the io.github.torkjacobs/tork-governance MCP server still maintained?

io.github.torkjacobs/tork-governance is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the io.github.torkjacobs/tork-governance MCP server under?

io.github.torkjacobs/tork-governance declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.