Zihin MCP Server
Zihin MCP Server is a proxy MCP stdio-to-HTTP server exposing the Zihin.ai platform (88 tools for admin, 48 for editor, 5 for member) so MCP clients can manage AI agents, tools, triggers, security policies, and converse with agents.
Session identity & chat:
whoami,list_published_agents,chat_with_agent(synchronous, session continuity viasession_id),get_session_history,list_agent_sessions.Agent lifecycle: create/update/delete/clone/publish/unpublish agents, plus
get_agent_full,list_agent_tools,validate_agent_schemas,get_agent_metrics.Schemas (persona, api_config, db_config, workflow, skill, MCP tool/resource): list/get/create/update/delete/toggle and dry-run
validate_schema_data.Triggers: webhook/db_event/email/schedule — create, update, delete, toggle, test, and inspect executions.
MCP servers (external tools): register, update, delete, test connectivity/handshake, invalidate tool cache.
Database connections: create/update/delete/test PostgreSQL or Supabase connections; inspect and refresh schema and semantic caches.
Secrets vault: list/create/update/delete AES-256-GCM encrypted secrets (plaintext never returned).
API keys: list/create/get/update (rate limit)/delete tenant keys with RBAC roles (admin/editor/member).
Security policies (CSPs): CRUD + toggle for schedule/behavior/data/origin/custom rules; resolve effective policies with scope inheritance.
HITL approvals: list pending approvals, and manage approval policies (stages/approvers).
Consumers: list consumers, get cross-session profiles, list their sessions, manual messaging, denylist control.
Session control: set engaged/suspended/manual_handoff, cancel in-flight agent turns (cascades to sub-agents).
Multi-agent & diagnostics: agent lineage, session agent tree, execution traces/diagnostics, tenant health.
Versioning & rollback: list/get/compare/rollback versions of agents, schemas, triggers, MCP servers; publication snapshots and snapshot rollback.
Memory & budgets: list/delete agent memories; get/list/set per-agent spend budgets.
Scheduler: view scheduler service status.
Resources & prompts: 19 resources (
zihin://agents,zihin://models,zihin://schema-templates,zihin://schemas/{tipo},zihin://skills/*) and 3 prompts (setup-agent,add-tool,configure-webhook); skills installable natively into Claude/Cursor/Windsurf/Codex.
Enables OpenAI Codex to discover and use Zihin's tools, resources, and prompts for managing agents, models, schemas, and more on the Zihin platform.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Zihin MCP Server list my agents and available LLM models"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Zihin MCP server
Connect MCP clients to the Zihin.ai agent platform. This package proxies stdio requests to the hosted MCP endpoint and includes platform skills. Requires Node.js 20 or later and a Zihin API key.
Quick start
ZIHIN_API_KEY=YOUR_ZIHIN_API_KEY npx -y @zihin/mcp-serverObtain your key from the Zihin console. Store it in your client's secret configuration. Use a key with the permissions needed for your work. Never commit it to a repository.
Related MCP server: OpenAPI to Model Context Protocol (MCP)
Client configuration
Add this entry to your MCP client's configuration:
{
"mcpServers": {
"zihin": {
"command": "npx",
"args": ["-y", "@zihin/mcp-server"],
"env": { "ZIHIN_API_KEY": "YOUR_ZIHIN_API_KEY" }
}
}
}Clients with Streamable HTTP support can connect directly to
https://llm.zihin.ai/mcp, using the X-Api-Key header.
Available tools and resources depend on your account and key permissions.
Claude Code plugin
/plugin marketplace add zihin-ai/zihin-mcp
/plugin install zihin@zihinEnter your key in the plugin's required, sensitive Zihin API key option. The plugin connects
directly to https://llm.zihin.ai/mcp over HTTP with the X-Api-Key header; it does
not start the npm proxy. Plugin versions advance independently of this package.
See the plugin guide for updates and configuration.
Cursor plugin
The Cursor plugin connects directly to the hosted MCP endpoint and includes the same
platform skills. Configure the required ZIHIN_API_KEY variable under Plugins → Configure.
The repository contains only the variable declaration; never commit the key or put it
in a prompt. The API key determines which operations are available. Agent execution
can consume credits and perform external actions.
Install skills
npx -y @zihin/mcp-server install-skills --client all --bundledSupported clients are claude, cursor, windsurf and codex. Use --dir to choose
the project directory, or --global for Claude's user-level skills. Without --bundled,
the installer fetches skills from the server using your API key and falls back to bundled
skills if the server cannot supply them. Existing skill identifiers are retained for compatibility.
Configuration
Variable | Purpose |
| Required API key |
| Optional trusted MCP endpoint; defaults to |
| Tool-call timeout in milliseconds; default 300000, range 1000–1800000 |
The proxy sends your key to the configured endpoint. Change the endpoint only for a trusted deployment. Diagnostics go to stderr; stdout carries MCP messages. Agent execution can consume credits and trigger external actions. Inspect returned errors and warnings before treating an operation as complete.
Development
npm ci
npm test
npm run check:publicationTests run offline without ZIHIN_API_KEY. Live integration tests require a test account
and key and can execute agents. REQUIRE_INTEGRATION=1 makes a missing key an error.
The publication check rejects unexpected package files and known language regressions;
release review must also check all public text and exact artifact contents.
Available Tools
113 toolsarchive_sessionAIdempotentInspect
Archive a conversation (leaves the active list; reversible)
Inputs: session_id (required).
attach_integration_credentialAInspect
Attach a credential from the company's own vault: integration_id, secret_ref (secret name; the platform/ namespace is reserved) and auth_kind (bearer, api_key, tunnel). One credential per integration; it cannot be replaced afterwards
Inputs: auth_kind (required), secret_ref (required), integration_id (required).
cancel_agent_turnADestructiveInspect
Cancel an in-progress agent turn (mid-LLM, mid-tool, mid-stream). Useful for loop runaway, off-target responses, or compliance stops. In multi-agent (sub-agent) sessions, propagates via root_execution_id
Inputs: session_id (required), reason.
cancel_process_instanceADestructiveInspect
Cancel a running process instance. Returns a command_id with status received — read the outcome with get_process_command
Inputs: instance_id (required), reason_note.
chat_with_agentAInspect
Send a message to a published agent. This executes the agent, consumes tokens and may cause external side effects. Reuse session_id for conversation context and client_message_id for idempotent retries. Shared admin/owner integrations must provide consumer_key to enable person-scoped memory. Returns response, execution/session identifiers, usage and structured blocks. See https://docs.zihin.ai/agents/invocation-contract.
Inputs: message (required), agent_id (required), context, bindings, +9 more. Returns: gated, usage, blocks, outcome, +20 more
clear_sessionADestructiveInspect
Irreversibly clear conversation history while preserving the conversation record. Returns SESSION_BUSY during an active turn or SERVICE_UNAVAILABLE when the delivery lock is unavailable. Requires the HTTP backend.
Inputs: session_id (required).
clone_agentBInspect
Clone agent with schemas and optionally triggers
Inputs: agent_id (required), new_name, include_schemas, include_triggers.
compare_versionsBRead-onlyIdempotentInspect
Compare two recorded versions of a configuration resource and inspect their changes.
Inputs: to_version (required), resource_id (required), from_version (required), resource_type (required).
create_agentAInspect
Create a draft agent and return its UUID. Add a persona with create_schema (persona_config), then publish_agent. Returns PLAN_LIMIT_REACHED when the tenant agent limit is reached. Read zihin://skills/criar-agente.
Inputs: name (required), bio, tags, type, +4 more.
create_api_keyBInspect
Create API Key with role (anti-escalation enforced)
Inputs: name (required), role, prefix, description, +2 more.
create_approval_policyCInspect
Create a policy. stages[].approvers accepts {type:"user", id} or {type:"role", role}
Inputs: name (required), stages (required), description.
create_cspAInspect
Create a contextual security policy with tenant, team, agent or user scope. Read zihin://schemas/csp_config: unknown rule fields may be accepted but have no effect. behavior.must_not_tools blocks named tools; execution ceilings use max_iterations, max_tool_calls and max_tokens_per_request. Native-chat human approval uses require_approval_for with tool names or matchers (tool_name, mcp_server_id, source=mcp|api) and approval_policy_id. Data rules are model instructions, not programmatic masking. origin policies are stored but not enforced; never use them as an access-control boundary. Custom rules become prompt instructions. See zihin://skills/governanca-e-operacao for examples.
Inputs: name (required), rules (required), scope (required), policy_type (required), +4 more.
create_integrationAInspect
Register an integration: kind (tunnel, api, mcp), name, target, shareable, limits. target and limits are immutable — to change them, create another integration
Inputs: kind (required), name (required), limits, target, +1 more.
create_mcp_serverAInspect
Register an external MCP server for an agent. Use http (Streamable HTTP) or stdio (local development). Authentication: none; bearer with config.vault_secret_id; api_key with vault_secret_id and optional api_key_header; tunnel uses platform authentication. timeout controls connection and tool discovery; call_timeout_ms controls each tool call (1000–120000 ms, default 30000). Timed-out calls are not retried automatically. Read zihin://schemas/mcp_resource_config for headers and defaults_from_context.
Inputs: name (required), agent_id (required), endpoint (required), config, +4 more.
create_schemaCInspect
Create schema with integrated validation
Inputs: agent_id (required), schema_data (required), schema_type (required), name, +1 more.
create_secretAInspect
Create an encrypted tenant secret. Save its value before submitting; plaintext is not returned afterward. Reference its name as secret_ref in API tools, MCP servers and trigger callbacks. Names starting with platform/ are reserved.
Inputs: name (required), value (required), category, usage_hint, +1 more.
create_triggerAInspect
Create a webhook, schedule or email trigger. Read zihin://schemas/trigger_config and use its exact enums. The server supplies tenant and record identifiers. The returned call block contains method, URL and authentication instructions; it does not return the API key value. Read zihin://skills/triggers-e-canais.
Inputs: name (required), agent_id (required), trigger_type (required), api_key_id, +2 more.
delete_agentADestructiveInspect
Archive an agent: remove it from listings and stop it responding. Restore through the Zihin console; this server has no restore tool.
Inputs: agent_id (required).
delete_agent_memoryADestructiveInspect
Delete one persistent agent memory. Platform control entries are protected and cannot be removed here.
Inputs: agent_id (required), user_key (required), memory_key (required), scope.
delete_api_keyADestructiveInspect
Revoke a tenant API key. Requests using that credential will no longer be authorized.
Inputs: key_id (required).
delete_cspADestructiveInspect
Permanently remove a contextual security policy and immediately remove its restrictions. Use toggle_csp to suspend it reversibly.
Inputs: csp_id (required).
delete_mcp_serverADestructiveInspect
Permanently remove an external MCP server from the agent configuration.
Inputs: mcp_server_id (required).
delete_schemaADestructiveInspect
Permanently remove an agent configuration schema. Its behavior or tool will no longer be available to the agent.
Inputs: schema_id (required).
delete_secretADestructiveInspect
Permanently delete a tenant secret. API tools, MCP servers and trigger callbacks that reference it will stop working.
Inputs: name (required).
delete_triggerADestructiveInspect
Permanently remove a trigger and stop its configured automation.
Inputs: trigger_id (required).
disable_processADestructiveIdempotentInspect
Remove permission to open new instances of a process, or use * for all. Existing instances continue. Permissions provided by server configuration cannot be removed here.
Inputs: scope (required).
enable_processAIdempotentInspect
Allow agents in this tenant to open a published process, or use * for all published processes. Takes effect immediately on this replica without restarting.
Inputs: scope (required).
get_agentBRead-onlyIdempotentInspect
Retrieve an agent configuration by UUID within the current tenant.
Inputs: agent_id (required). Returns: agent, success
get_agent_budgetARead-onlyIdempotentInspect
Get the current agent spending cap and cycle balance in USD. Includes all model calls, including BYOK; unlimited=true means no cap.
Inputs: agent_id (required).
get_agent_fullBRead-onlyIdempotentInspect
Complete agent view (schemas + triggers + CSPs)
Inputs: agent_id (required).
get_agent_lineageARead-onlyIdempotentInspect
Orchestrator→sub-agent pairs that actually invoked each other (via invoke_agent), with invocation counts — complements allowed_invoke_agents (which is "may invoke")
Inputs: no named parameters.
get_agent_metricsARead-onlyIdempotentInspect
Execution metrics by period (1d, 7d, 30d): LLM calls, errors, success rate, tokens, cost, p50/p95 latency (aggregated server-side — no row cap), tool usage (sampled, with sample_truncated disclosure) and sessions
Inputs: agent_id (required), period. Returns: llm, since, tools, period, +2 more
get_api_keyARead-onlyIdempotentInspect
Retrieve metadata for a tenant API key. The secret key value is not returned.
Inputs: key_id (required).
get_approval_policyCRead-onlyIdempotentInspect
Policy details (name, stages, approvers, is_active)
Inputs: policy_id (required).
get_consumer_profileARead-onlyIdempotentInspect
Get aggregated consumer profile (cross-session, cross-agent): display name, channels used, total sessions, total turns, agents interacted, product flags, timestamps
Inputs: consumer_key (required).
get_cspARead-onlyIdempotentInspect
Retrieve one contextual security policy and its configured rules.
Inputs: csp_id (required).
get_effective_cspsCRead-onlyIdempotentInspect
Inspect the contextual security policies effective for the requested scope.
Inputs: team_id, user_id, agent_id.
get_execution_diagnosticsARead-onlyIdempotentInspect
Get execution diagnostics: chronological model and tool calls, tokens, latency, model, finish_reason, cache reads/writes and caller correlation metadata. Use the execution_id or root_execution_id returned by chat_with_agent.
Inputs: execution_id (required). Returns: success, summary, timeline, execution
get_execution_traceBRead-onlyIdempotentInspect
Hierarchical multi-agent execution trace from a root_execution_id: supervisor→sub-agents with phases, tool calls and cost per node
Inputs: root_execution_id (required).
get_mcp_serverARead-onlyIdempotentInspect
Retrieve an external MCP server configuration by its UUID.
Inputs: mcp_server_id (required).
get_process_commandARead-onlyIdempotentInspect
Outcome of an intervention command: received (not applied yet), applied or rejected (with reason). Query this instead of repeating the mutation
Inputs: command_id (required), instance_id (required).
get_process_definitionARead-onlyIdempotentInspect
Get a complete process definition and its version history. Omit version for the latest published version; inspect it before publishing a new one.
Inputs: key (required), version.
get_process_engine_statusBRead-onlyIdempotentInspect
Whether the engine is enabled for the tenant
Inputs: no named parameters.
get_process_instanceARead-onlyIdempotentInspect
Inspect a process instance. Editors see status, steps, agent, name and dates. Admin/owner roles also see redacted variables, human tasks, file metadata and computation summaries.
Inputs: instance_id (required).
get_process_trailARead-onlyIdempotentInspect
Read a process instance audit trail in order, including transitions, triggering events/commands and reasons. Sensitive values are redacted. Requires admin or owner.
Inputs: instance_id (required), limit, after_sequence.
get_scheduler_statusCRead-onlyIdempotentInspect
Status of active scheduled triggers (cron jobs)
Inputs: no named parameters.
get_schemaBRead-onlyIdempotentInspect
Retrieve one agent configuration schema and its current version.
Inputs: schema_id (required).
get_session_agent_treeARead-onlyIdempotentInspect
Agent tree of a session (by parent-session lineage): supervisor + sub-agents across all turns — works where per-execution traces can't close the tree in multi-turn sessions
Inputs: session_id (required), execution_id.
get_session_historyARead-onlyIdempotentInspect
Message history of a session, read from the durable record and paginated with before/limit/next_before (user/assistant messages only; attachments as metadata) — see below
Inputs: session_id (required), limit, before. Returns: success, agent_id, messages, session_id, +2 more
get_session_trigger_contextBRead-onlyIdempotentInspect
Reverse lookup: given a session_id, returns the trigger and execution that originated the session
Inputs: session_id (required).
get_snapshotARead-onlyIdempotentInspect
Retrieve a publication snapshot and inspect its saved configuration before restoration.
Inputs: snapshot_id (required).
get_tenant_healthARead-onlyIdempotentInspect
Tenant-level infra errors not attributable to a specific agent (provider auth, rate limit), grouped by canonical error code
Inputs: end_date, start_date.
get_triggerBRead-onlyIdempotentInspect
Retrieve a trigger and its current configuration before inspection or update.
Inputs: trigger_id (required).
get_trigger_executionARead-onlyIdempotentInspect
Retrieve one trigger execution and its recorded outcome for troubleshooting.
Inputs: execution_id (required).
get_versionARead-onlyIdempotentInspect
Retrieve one recorded resource version for inspection before restoring it.
Inputs: version (required), resource_id (required), resource_type (required).
grant_integrationAInspect
Give a consumer access: integration_id, consumer_tenant_id, optional consumer_agent_id (absent = the whole company), allowed_operations (absent or empty = all operations) and expires_at (ISO 8601). The grant is created active and applies on the consumer's next call
Inputs: integration_id (required), consumer_tenant_id (required), expires_at, consumer_agent_id, +1 more.
invalidate_mcp_cacheAIdempotentInspect
Invalidate cached discovery for an external MCP server after its available tools change.
Inputs: mcp_server_id.
list_agent_budgetsARead-onlyIdempotentInspect
Get current USD spending caps and balances for all tenant agents in one call. Includes BYOK usage.
Inputs: no named parameters.
list_agent_historyARead-onlyIdempotentInspect
List an agent's recorded change history to investigate configuration changes.
Inputs: agent_id (required), limit, offset, resource_type.
list_agent_memoryCRead-onlyIdempotentInspect
List persistent memory entries for an agent
Inputs: agent_id (required), limit, scope, before, +3 more.
list_agentsBRead-onlyIdempotentInspect
List tenant agents (filters: status, type, include_archived)
Inputs: type, status, include_archived, include_unpublished. Returns: count, agents, success
list_agent_sessionsARead-onlyIdempotentInspect
List recent conversations with an agent, newest first; status selects active (default) or archived sessions. Members see their own sessions; operators see tenant sessions. message_count and last_message_preview cover up to 50 recent messages, while total counts all matching sessions. offset must be a multiple of limit.
Inputs: agent_id (required), limit, offset, status, +3 more. Returns: total, success, sessions
list_agent_toolsCRead-onlyIdempotentInspect
All resolved tools (api_config + MCP + core), with resolved/error status
Inputs: agent_id (required).
list_api_keysARead-onlyIdempotentInspect
List tenant API key metadata without exposing secret key values.
Inputs: no named parameters.
list_approval_policiesCRead-onlyIdempotentInspect
Approval policies (filter active_only)
Inputs: active_only.
list_approvalsARead-onlyIdempotentInspect
Pending approval requests for the tenant. admin/owner see all; editor is scoped to own requests + what they can approve
Inputs: limit, status.
list_consumersARead-onlyIdempotentInspect
Paginated list of consumers, ordered by last_seen_at (desc). Filters: search (substring in display_name or consumer_key), blocked (true = only denylisted, false = only not-denylisted)
Inputs: limit, offset, search, blocked.
list_consumer_sessionsARead-onlyIdempotentInspect
Paginated list of a specific consumer's sessions (cross-agent, most recent first) — complements get_consumer_profile, which returns only aggregated counters
Inputs: consumer_key (required), limit, offset.
list_cspsBRead-onlyIdempotentInspect
List contextual security policies in the current tenant.
Inputs: scope, is_active, policy_type, scope_target_id.
list_executionsARead-onlyIdempotentInspect
Search the tenant's agent executions, most recent first, with pagination (page, limit). Filters: trace_id (the correlation id the integrator sent in metadata.trace_id), session_id, agent_id, status, source (chat, sse, mcp_server, webhook, schedule, email, task, builder, process), start_date/end_date (ISO 8601). Same as GET /api/v1/executions. For one execution's detail use get_execution_diagnostics; for the multi-agent tree, get_execution_trace
Inputs: page, limit, source, status, +5 more.
list_integration_grantsARead-onlyIdempotentInspect
Grants where this company is the owner (as: "owner", what it gives) or the consumer (as: "consumer", the default — what it receives)
Inputs: as.
list_integrationsBRead-onlyIdempotentInspect
Integrations this company owns (items, total)
Inputs: no named parameters.
list_mcp_serversBRead-onlyIdempotentInspect
List the external MCP servers configured for an agent.
Inputs: agent_id (required), status.
list_process_definitionsARead-onlyIdempotentInspect
List the latest published definition for each process key in the tenant, including its version, steps and availability to agents. Agents open instances with open_process.
Inputs: no named parameters.
list_process_instancesARead-onlyIdempotentInspect
List tenant process instances, newest first, with status, current step and owner. Filter by open/closed state or definition; use get_process_instance for details.
Inputs: open, limit, before, definition_key.
list_published_agentsARead-onlyIdempotentInspect
List published agents available for chat
Inputs: no named parameters. Returns: agents, success
list_schemasCRead-onlyIdempotentInspect
List schemas for an agent (filters: schema_type, include_inactive)
Inputs: agent_id (required), schema_type, include_inactive.
list_secretsARead-onlyIdempotentInspect
List tenant secret metadata without exposing credential values. Use each name as secret_ref where supported.
Inputs: no named parameters.
list_snapshotsBRead-onlyIdempotentInspect
List an agent's publication snapshots available for inspection or restoration.
Inputs: agent_id (required), limit, offset.
list_trigger_executionsBRead-onlyIdempotentInspect
List execution records for a trigger to inspect recent runs and delivery results.
Inputs: trigger_id (required), limit, offset.
list_triggersCRead-onlyIdempotentInspect
List triggers (filters: agent_id, trigger_type, enabled)
Inputs: enabled, agent_id, trigger_type.
list_versionsARead-onlyIdempotentInspect
List recorded versions of a configuration resource for inspection or rollback.
Inputs: resource_id (required), resource_type (required), limit, offset.
publish_agentBIdempotentInspect
Publish agent (validates all schemas first)
Inputs: action (required), agent_id (required).
publish_process_definitionAInspect
Publish the next version of a process definition. New instances use it; existing instances retain their original version. Validate first. Worker request recipes belong to the definition; agents select among its allowed recipes.
Inputs: spec (required).
ratify_integration_grantAInspect
Confirm a provisional grant (pending_ratification → active), e.g. one registered by a migration. Repeating it on an active grant returns the grant unchanged
Inputs: grant_id (required).
resolve_process_incidentCDestructiveInspect
Resolve an incident of a process instance (same command_id pattern)
Inputs: resolution (required), instance_id (required), task_id, substitute_output.
retire_process_definitionADestructiveInspect
Retire all published versions of a process key to prevent new instances. Existing instances continue. Publish a new version to make the process available again.
Inputs: key (required).
revoke_integration_grantADestructiveInspect
Revoke a grant. Takes effect on the next call. A revoked grant cannot be reactivated — grant again instead. Repeating it returns the grant unchanged
Inputs: grant_id (required).
rollback_snapshotADestructiveInspect
Restore an agent from a previous publication snapshot, overwriting its current configuration, schemas, triggers and MCP servers. Inspect get_snapshot before restoring.
Inputs: snapshot_id (required).
rollback_versionBDestructiveInspect
Restore a resource from a recorded version, replacing its current configuration.
Inputs: resource_id (required), resource_type (required), target_version (required).
send_manual_messageAInspect
Send a manual operator message through the same outbound channel as the agent (Twilio/Meta/webhook). Requires control_mode != engaged. Message is recorded as human-authored so the agent doesn't imitate the style if it resumes
Inputs: message (required), session_id (required), idempotency_key.
set_agent_budgetAIdempotentInspect
Set or remove the cap (limit_usd: null = unlimited). Also the recovery loop: raising the cap lets a budget-stopped agent run again on the next turn
Inputs: agent_id (required), limit_usd (required).
set_consumer_denylistAIdempotentInspect
Add or remove a consumer from the tenant-wide denylist. When active, all messages from that consumer are bypassed cross-agent (no LLM, no quota)
Inputs: blocked (required), consumer_key (required), reason, message.
set_engagement_controlAIdempotentInspect
End or restore the engagement between one agent and one consumer, without blocking the consumer tenant-wide. Evaluated after the tenant denylist and before session control
Inputs: action (required), agent_id (required), user_key (required), reason, +2 more.
set_session_controlBIdempotentInspect
Change a session's control_mode (engaged, suspended, manual_handoff). When ≠ engaged, the agent loop is bypassed for new messages on that session
Inputs: mode (required), session_id (required), reason, message, +1 more.
test_mcp_serverAInspect
Perform a real MCP handshake and list external tools to check connectivity, authentication and protocol compatibility. Updates the stored server status, last error and protocol version. success=true means the test ran; reachable is its result. Inspect error_class and error_message when unreachable.
Inputs: mcp_server_id (required).
test_triggerAInspect
Execute a trigger with a test payload. This runs the agent, consumes tokens and may cause external side effects.
Inputs: trigger_id (required), test_payload.
toggle_cspAInspect
Enable or disable a contextual security policy. Inactive policies are not applied. Set enabled for the desired state; omitting it toggles the current state. Concurrent calls can race, so verify the returned is_active value.
Inputs: csp_id (required), enabled.
toggle_schemaAInspect
Enable or disable a schema without deleting it. Inactive schemas are not loaded by the agent. Set enabled for the desired state; omitting it toggles the current state. Concurrent calls can race, so verify the returned is_active value.
Inputs: schema_id (required), enabled.
toggle_triggerAInspect
Enable or disable a trigger without deleting its configuration. Set enabled for the desired state; omitting it toggles the current state. Concurrent calls can race, so verify the returned is_active value.
Inputs: enabled (required), trigger_id (required).
unarchive_sessionAIdempotentInspect
Bring an archived conversation back to the active list. CONFLICT if it was not archived
Inputs: session_id (required).
update_agentAIdempotentInspect
Update only the supplied agent fields. memory_enabled, quick_replies_enabled and engagement_control_enabled change the agent tool surface and require admin/owner. chat_enabled controls native chat availability. Inspect partial_update if only part of the update succeeded.
Inputs: agent_id (required), bio, name, tags, +9 more.
update_api_keyBIdempotentInspect
Update the supplied API key settings within the caller's permissions and tenant plan limits.
Inputs: key_id (required), rate_limit_per_minute (required).
update_approval_policyAIdempotentInspect
Update name/description/stages or deactivate (is_active: false)
Inputs: policy_id (required), name, stages, is_active, +1 more.
update_cspAIdempotentInspect
Update a contextual security policy. Supplied rules replace the whole object; include all fields to retain. Check zihin://schemas/csp_config because unknown fields may be accepted without effect. Use behavior.must_not_tools for tool restrictions and require_approval_for with approval_policy_id for native-chat human approval.
Inputs: csp_id (required), name, rules, priority, +2 more.
update_mcp_serverAIdempotentInspect
Update only supplied MCP server fields. config replaces the whole object; send all settings to retain. Changes invalidate the agent tool surface; connection, configuration, authentication and transport changes also invalidate server tool discovery.
Inputs: mcp_server_id (required), name, config, status, +5 more.
update_schemaAIdempotentInspect
Update an agent schema using its current base_version. Supplied schema_data replaces the full document; reload and reconcile on CONFLICT.
Inputs: schema_id (required), changelog, schema_data, base_version.
update_secretAIdempotentInspect
Replace a tenant secret value with a newly encrypted value. Existing references keep using the same secret name.
Inputs: name (required), value (required), description.
update_triggerAIdempotentInspect
Update only supplied trigger fields. trigger_config replaces the entire configuration; read get_trigger first and include all settings to retain.
Inputs: trigger_id (required), name, api_key_id, description, +1 more.
validate_agent_schemasARead-onlyIdempotentInspect
Validate an agent's configured schemas and report errors and warnings before publication.
Inputs: agent_id (required).
validate_process_definitionARead-onlyIdempotentInspect
Validate a process definition without saving: structure, execution rules and tenant ownership of referenced agents, approval policies and MCP servers. Returns errors with paths and reasons. Run before publishing.
Inputs: spec (required).
validate_schema_dataARead-onlyIdempotentInspect
Dry-run: validate schema data without saving — same server-side JSON Schema validation as create_schema/update_schema. Supports all canonical types, including trigger_config and csp_config
Inputs: schema_data (required), schema_type (required). Returns: infos, valid, errors, warnings
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 113 tools
Most tools have a clear resource+action identity and the descriptions are unusually detailed, which helps a lot. However, several clusters overlap enough to cause misselection: list_versions/get_version/compare_versions/rollback_version vs list_snapshots/get_snapshot/rollback_snapshot vs list_agent_history, and list_agents vs list_published_agents vs get_agent vs get_agent_full. Session-oriented tools (list_agent_sessions, list_consumer_sessions, list_executions, get_session_history, get_session_agent_tree) also require careful reading to distinguish.
The dominant pattern is consistent snake_case verb_noun (list_agents, create_trigger, delete_csp, update_mcp_server), applied across the large majority of the surface. Deviations are minor: whoami (no verb), get_agent_full, get_effective_csps, invalidate_mcp_cache, and enable_process/disable_process sitting alongside the toggle_* family.
113 tools is far beyond a comfortable surface for an agent to select from, even granting that the platform genuinely spans agents, schemas, triggers, MCP servers, CSPs, secrets, budgets, approvals, integrations, executions and processes. Several tools are near-redundant conveniences (get_agent_budget vs list_agent_budgets, get_agent vs get_agent_full, get_version vs get_snapshot) that suggest the set should be consolidated or split into sub-servers.
Coverage is broad and lifecycle-oriented in most areas (agents, schemas, triggers, MCP servers, CSPs, secrets, versions, processes), but there are real dead ends: list_approvals has no approve/reject tool, approval policies have CRUD minus delete, agent memory can be listed and deleted but not created, integrations have create/grant/revoke but no update or delete, and delete_agent explicitly has no restore counterpart in this server.
Maintenance
Related MCP Connectors
MCP gateway and cloud hosting for MCP servers, agents and apps like RAG, managed from your agent.
MCP server for building and testing AI agents with multi-model experimentation and insights.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server connecting AI agents to 100+ apps (Gmail, Slack, Notion, GitHub) via one-click OAuth.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA proxy server that unifies multiple MCP servers, enabling seamless tool, prompt, and resource management via the MetaMCP App.67 npm155Apache 2.0
- AlicenseNot gradedqualityCmaintenanceA proxy server that bridges AI agents and external APIs by dynamically translating OpenAPI specifications into standardized MCP tools, enabling seamless interaction without custom integration code.57 PyPI69MIT
- FlicenseNot gradedqualityDmaintenanceA centralized management platform that aggregates multiple Model Context Protocol (MCP) servers into a single unified endpoint for AI agents. It provides a web interface for hot-swappable tool management, proxying of existing servers, and AI-powered generation of custom MCP plugins.1-
- AlicenseNot gradedqualityDmaintenanceActs as an intermediary between LLMs and other MCP servers, centralizing management, sanitizing sensitive information, and providing a unified interface for discovering and interacting with proxied MCPs.403MIT