List your agents — List all agents owned by the authenticated user. Supports pagination.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many agents to return, 1-100. | |
| offset | No | How many agents to skip, for pagination. |
| Name | Required | Description | Default |
|---|---|---|---|
| scope | Yes | Echoes the resolved listing scope. | |
| agents | Yes | The caller's agents, reduced to the MCP trust-loop field set. |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / limit / descriptionPrevious value: -"Maximum number of agents to return (max 100)"New value: +"How many agents to return, 1-100."Input schema / properties / limit / minimumAdded value: +1Input schema / properties / offset / descriptionPrevious value: -"Number of agents to skip for pagination"New value: +"How many agents to skip, for pagination."Input schema / properties / offset / maximumAdded value: +100000Input schema / properties / offset / minimumAdded value: +0Output schema / $defs / AgentRemoved value: -{
- "additionalProperties": true,
- "description": "An agent. GET /v1/agents/{id} returns one of TWO projections by authorization: an ORGANIZATION-MEMBER (owner) caller receives the full agent row (all fields below); a NON-OWNER receives a reduced public projection (id, name, claimed, created_at, last_seen, status, avatar_url). additionalProperties is left open because the owner row is the full DB row and grows as agent-settings columns are added (ADR-053 / proof / DDR); over-constraining it would 500 the endpoint on the next migration under /v1 response enforcement.",
- "properties": {
- "agent_hash": {
- "description": "First 16 hex chars of `SHA256(apiKey + '|' + agentName)` for named agents, or `SHA256(apiKey)` for unnamed singleton agents. The gateway computes the same value on each request and uses it as the lookup key. See [Agent Identity](https://docs.mnemom.ai/concepts/agent-identity#agent_hash--the-canonical-identity-hash).",
- "example": "a1b2c3d4e5f6a7b8",
- "type": "string"
- },
- "agent_proof_captured_at": {
- "format": "date-time",
- "type": [
- "string",
- "null"
- ]
- },
- "agent_proof_hash": {
- "description": "Owner projection: captured hash_proof of the bound key (mig 263).",
- "type": [
- "string",
- "null"
- ]
- },
- "aip_enforcement_mode": {
- "enum": [
- "observe",
- "enforce",
- "nudge"
- ],
- "type": [
- "string",
- "null"
- ]
- },
- "avatar_url": {
- "type": [
- "string",
- "null"
- ]
- },
- "billing_account_id": {
- "type": [
- "string",
- "null"
- ]
- },
- "caller": {
- "description": "Self-describing caller context for THIS response. `org_member` callers receive the full owner record (all fields here); `anonymous`/`authenticated` (non-member) callers receive the reduced public projection (id, name, claimed, created_at, last_seen, status, avatar_url, caller). The differing field set is GOVERNED by this value — read it instead of inferring why a field is absent.",
- "enum": [
- "anonymous",
- "authenticated",
- "org_member"
- ],
- "type": "string"
- },
- "claimed": {
- "description": "Public projection only: whether the agent has been claimed by a user.",
- "type": "boolean"
- },
- "claimed_at": {
- "format": "date-time",
- "type": [
- "string",
- "null"
- ]
- },
- "claimed_by": {
- "description": "Owner projection: user id that claimed the agent.",
- "type": [
- "string",
- "null"
- ]
- },
- "containment_status": {
- "description": "Containment state of the agent (ADR-053).",
- "enum": [
- "active",
- "paused",
- "killed"
- ],
- "type": [
- "string",
- "null"
- ]
- },
- "created_at": {
- "format": "date-time",
- "type": "string"
- },
- "created_by": {
- "description": "Owner projection: user id that created the agent (provenance).",
- "type": [
- "string",
- "null"
- ]
- },
- "deleted_at": {
- "description": "Owner projection: soft-delete timestamp (null when live).",
- "format": "date-time",
- "type": [
- "string",
- "null"
- ]
- },
- "email": {
- "type": [
- "string",
- "null"
- ]
- },
- "groups": {
- "description": "Active groups this agent belongs to, name-ordered; `[]` when none. Present on org-fleet rows (GET /v1/orgs/{org_id}/agents). Archived groups are excluded.",
- "items": {
- "properties": {
- "color": {
- "description": "Group color (hex, e.g. `#0d9488`); `null` when unset.",
- "type": [
- "string",
- "null"
- ]
- },
- "id": {
- "type": "string"
- },
- "name": {
- "type": "string"
- }
- },
- "required": [
- "id",
- "name",
- "color"
- ],
- "type": "object"
- },
- "type": "array"
- },
- "id": {
- "type": "string"
- },
- "key_prefix": {
- "description": "First 8 chars of the bound API key hash — useful for key-rotation debugging.",
- "type": [
- "string",
- "null"
- ]
- },
- "last_seen": {
- "format": "date-time",
- "type": [
- "string",
- "null"
- ]
- },
- "name": {
- "description": "Agent name (2-32 chars, alphanumeric + hyphens). Present on all list and get responses.",
- "type": [
- "string",
- "null"
- ]
- },
- "org_id": {
- "description": "Owner projection: the agent's org binding (ADR-062 authz boundary).",
- "type": [
- "string",
- "null"
- ]
- },
- "public": {
- "description": "Identity-record visibility axis — whether the agent's IDENTITY RECORD is publicly discoverable. This is DISTINCT from reputation visibility: every registered agent's reputation is public by accountability standard (see `ReputationScore.visibility`). `public` here governs only the identity record, never the Trust Rating.",
- "type": "boolean"
- },
- "status": {
- "enum": [
- "active",
- "offline"
- ],
- "type": "string"
- },
- "user_id": {
- "type": [
- "string",
- "null"
- ]
- }
- },
- "type": "object"
-}Output schema / $defs / AgentMcpRecordAdded value: +{
+ "additionalProperties": false,
+ "description": "An agent's identity and trust state, reduced to the fields the trust loop needs. Personal data (owner email address, user identifiers), internal commercial identifiers (billing account) and key-material-derived values (bound-key proof hash, key prefix) are REMOVED at the MCP boundary and are never returned to an MCP client — see the Mnemom privacy policy at https://www.mnemom.ai/privacy. Which fields are present depends on authorization: read `caller` to know which projection you received.",
+ "properties": {
+ "agent_hash": {
+ "description": "The canonical public identity hash (first 16 hex chars) used as the gateway lookup key and as the input to verify_agent_binding. Owner projection only. Not a credential and not reversible to one.",
+ "type": "string"
+ },
+ "aip_enforcement_mode": {
+ "enum": [
+ "observe",
+ "enforce",
+ "nudge"
+ ],
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "avatar_url": {
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "caller": {
+ "description": "Which projection THIS response is. `org_member` receives the owner field set; `anonymous`/`authenticated` receive the reduced public set (id, name, claimed, created_at, last_seen, status, avatar_url, caller). Read this instead of inferring why a field is absent.",
+ "enum": [
+ "anonymous",
+ "authenticated",
+ "org_member"
+ ],
+ "type": "string"
+ },
+ "claimed": {
+ "description": "Whether a human or organization has claimed accountability for this agent. On the owner projection this is derived from the ownership column; the owning user's identifier itself is not returned.",
+ "type": "boolean"
+ },
+ "claimed_at": {
+ "format": "date-time",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "containment_status": {
+ "description": "Containment state of the agent.",
+ "enum": [
+ "active",
+ "paused",
+ "killed"
+ ],
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "created_at": {
+ "format": "date-time",
+ "type": "string"
+ },
+ "groups": {
+ "description": "Active groups this agent belongs to, name-ordered; `[]` when none. Present on org-fleet rows.",
+ "items": {
+ "properties": {
+ "color": {
+ "description": "Group color (hex, e.g. `#0d9488`); `null` when unset.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "id": {
+ "type": "string"
+ },
+ "name": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "name",
+ "color"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "id": {
+ "description": "Agent identifier (e.g. smolt-abc123).",
+ "type": "string"
+ },
+ "last_seen": {
+ "format": "date-time",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "name": {
+ "description": "Agent name (2-32 chars, alphanumeric + hyphens).",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "org_id": {
+ "description": "The agent's organization binding. Required as an input by the org-scoped tools (fleet listing, posture assignment). Identifies an organization, not a person.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "public": {
+ "description": "Whether the agent's identity record is publicly discoverable. Distinct from Trust Rating visibility, which is always public.",
+ "type": "boolean"
+ },
+ "status": {
+ "description": "Derived from last_seen (active = seen within the last hour).",
+ "enum": [
+ "active",
+ "offline"
+ ],
+ "type": "string"
+ }
+ },
+ "required": [
+ "id"
+ ],
+ "type": "object"
+}Output schema / properties / agents / descriptionAdded value: +"The caller's agents, reduced to the MCP trust-loop field set."Output schema / properties / agents / items / $refPrevious value: -"#/$defs/Agent"New value: +"#/$defs/AgentMcpRecord"Output schema / $defs / Agent / properties / groupsAdded value: +{
+ "description": "Active groups this agent belongs to, name-ordered; `[]` when none. Present on org-fleet rows (GET /v1/orgs/{org_id}/agents). Archived groups are excluded.",
+ "items": {
+ "properties": {
+ "color": {
+ "description": "Group color (hex, e.g. `#0d9488`); `null` when unset.",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "id": {
+ "type": "string"
+ },
+ "name": {
+ "type": "string"
+ }
+ },
+ "required": [
+ "id",
+ "name",
+ "color"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / $defs / Agent / properties / aap_enabledRemoved value: -{
- "description": "Owner projection: AAP pipeline enabled.",
- "type": "boolean"
-}Output schema / $defs / Agent / properties / aip_enabledRemoved value: -{
- "description": "Owner projection: AIP pipeline enabled.",
- "type": "boolean"
-}Output schema / $defs / Agent / properties / analyze_outputRemoved value: -{
- "description": "Owner projection: analyze agent output.",
- "type": [
- "boolean",
- "null"
- ]
-}Output schema / $defs / Agent / properties / ddr_modeRemoved value: -{
- "description": "Owner projection: drift-detection-response mode (mig default 'flag').",
- "type": "string"
-}Output schema / $defs / Agent / properties / nudge_strategyRemoved value: -{
- "description": "Owner projection: nudge strategy.",
- "type": [
- "string",
- "null"
- ]
-}Output schema / $defs / Agent / properties / proof_enabledRemoved value: -{
- "description": "Owner projection: proof capture enabled.",
- "type": "boolean"
-}Output schema / $defs / Agent / properties / proof_rateRemoved value: -{
- "description": "Owner projection: proof sampling rate (0–100%).",
- "type": "integer"
-}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is known. The description adds the scope constraint ('owned by the authenticated user') and pagination support, which is helpful. However, it does not disclose ordering, error cases, or rate limits, so it only moderately adds beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the action and resource, then a clarifying detail. Every word earns its place; there is no fluff or redundancy. The dash separator improves readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With high annotation coverage, a fully described input schema, and an existing output schema, the description is complete for a simple read-only list operation. It correctly mentions pagination and the ownership scoping, which are the only non-obvious aspects beyond the structured data.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both limit and offset parameters already fully described in the schema. The tool description only says 'Supports pagination,' which adds no additional meaning beyond the schema. Baseline of 3 is appropriate because the schema carries the parameter documentation burden.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description uses a specific verb and resource: 'List your agents — List all agents owned by the authenticated user.' It clearly distinguishes from sibling tools like get_agent (which fetches a single agent) and claim_agent (which assigns ownership). The scope is explicit and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states it lists agents owned by the authenticated user and supports pagination, providing clear context for when to use this tool. It does not explicitly name alternatives or exclusions, but the sibling list hints at differentiated use cases. A stronger statement like 'use this instead of get_agent for all agents' would earn a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct operation: identity claiming, lookup, reputation retrieval/badge, scanning, verification, alignment/protection management, and feedback. No significant overlap exists.
All tools follow a consistent verb_noun pattern using snake_case (e.g., claim_agent, get_reputation, verify_scan). Even complex names like preview_compose_alignment_by_agent adhere to the pattern.
With 16 tools, the set is slightly heavy but still well-scoped for the domain of AI agent trust ratings. Each tool serves a clear purpose, and no tool feels redundant.
The surface covers core workflows: agent identity, reputation, alignment/protection, scanning, verification, and feedback. Minor gaps like agent updates or deletion might exist, but the core lifecycle is complete.