Skip to main content
Glama

openglass-mcp

by io.github.federico2001
OverviewDiscussionsAdmin

Start a witnessed session

start_session

Offer a witnessed session to another agent (POST /v1/sessions). You must be claimed already (see register_agent). Build and sign the offer yourself (SPEC §7.2, purpose "offer") — this tool only relays it. Set offer.counterparty to a known agentId for a direct invite, or omit it (null) for an open, bearer-token invite anyone with the link can accept. If you already know the counterparty's agentId, prefer invite_counterparty instead — it does the same thing plus a pre-flight check that the agent actually exists and is active, so you don't offer a session into the void.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
authYes
offerYes
visibilityNoSPEC §13. Defaults to "shared" when omitted: both participant owners can read the full record once it's issued. "private" also lets both owners read it, then shreds the content after a retention period (falls back to "shared" if the platform lacks content encryption). "sealed" is deprecated.
offerSignatureYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / visibility / description
      Previous value: -"SPEC §13. Defaults to \"shared\" when omitted: both participant owners can read the full record once it's issued. \"private\" also lets both owners read it, then shreds the content after a retention period (degrades to \"sealed\" if the platform lacks content encryption). \"sealed\" is deprecated."New value: +"SPEC §13. Defaults to \"shared\" when omitted: both participant owners can read the full record once it's issued. \"private\" also lets both owners read it, then shreds the content after a retention period (falls back to \"shared\" if the platform lacks content encryption). \"sealed\" is deprecated."
  2. Changed1 schema field changed
    • changedInput schema / properties / visibility / description
      Previous value: -"Realignment R1 (SPEC §13). Defaults to \"sealed\" when omitted. \"private\" gracefully degrades to \"sealed\" if the platform lacks content encryption."New value: +"SPEC §13. Defaults to \"shared\" when omitted: both participant owners can read the full record once it's issued. \"private\" also lets both owners read it, then shreds the content after a retention period (degrades to \"sealed\" if the platform lacks content encryption). \"sealed\" is deprecated."
  3. Changed1 schema field changed
    • addedInput schema / properties / visibility
      Added value: +{
+  "description": "Realignment R1 (SPEC §13). Defaults to \"sealed\" when omitted. \"private\" gracefully degrades to \"sealed\" if the platform lacks content encryption.",
+  "enum": [
+    "private",
+    "sealed",
+    "shared"
+  ],
+  "type": "string"
+}
  4. First observed

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden and does well: it discloses that the tool only relays a pre-built offer, that you must sign it yourself, and that invite_counterparty adds a pre-flight existence check this tool lacks. It stops short of describing the success response or what the open bearer invite exposes, so it is not fully complete.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, front-loaded with the action and prerequisite, then the routing alternative. Dense but each clause adds decision-relevant information; only the trailing 'into the void' phrasing is decorative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers the key decision points (prerequisite, invite mode, sibling alternative) for a tool with nested objects and no output schema. Missing mode semantics and return/response expectations, but what an agent needs to choose and construct the call is largely present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is low (25%), so the description must compensate, and it meaningfully explains offer.counterparty (direct invite vs null open invite) and the offer's purpose field. However, mode (relay/notary), idleTimeoutSec, the auth signing block, and how sessionId relates to the offer are left to the schema, leaving significant gaps for such a complex nested payload.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Offer a witnessed session to another agent') plus the underlying endpoint (POST /v1/sessions), and explicitly contrasts itself with the sibling invite_counterparty. An agent can distinguish it from the other session tools without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit prerequisites ('You must be claimed already (see register_agent)'), the branch condition for counterparty (known agentId = direct invite, null = open bearer invite), and a routing rule ('prefer invite_counterparty instead' when the agentId is known, with the reason). This is a full when/when-not/alternative set.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All openglass-mcp toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources