Skip to main content
Glama

NASC: Networked AI Session Continuity

nasc_intake

Imports history into this org's brain: vendor export zips (Claude, ChatGPT), transcript files (JSON, JSONL), CLI and IDE session databases (Cursor, VS Code, Goose), and note exports (Obsidian, Notion and similar), which stage verbatim as wiki candidates. Files land in the org's private storage; a worker parses them, deduplicated against live capture, and a human approves in the Control Panel before any AI reads them. request mints signed upload slots, requires files and consent_version, recorded only after the user explicitly confirms consent to upload this data. Each file is PUT to its signedUrl, then finalize takes run_id and sha256; nothing unverified is parsed. runs lists this org's runs. Requires an owner or admin seat.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "nasc_intake"
  }
}

Input Schema

NameRequiredDescriptionDefault
whoNoOperator name label. Attribution comes from the authenticated account.
brainNoOptional target org (brain uuid). Ignored unless this account can already access it; it never grants access.
filesNorequest: max 20 files, 200MB each; zip, json, jsonl, ndjson.gz, db, sqlite or vscdb by default.
actionYes
run_idNofinalize: run uuid from request.
sha256Nofinalize: lowercase hex sha256 of the uploaded bytes.
session_idNoOptional session id from nasc_start. Pins this call's authorization, org and project to that session.
consent_versionNorequest: the consent statement version the user explicitly acknowledged in conversation (e.g. 'mcp-v1'). Required, and only valid with the user's explicit go-ahead.
continuity_tokenNoOptional host conversation id. Resolves the active session and pins this call's authorization, org and project to it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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 supplied, the description carries the full burden and largely meets it: it discloses that files land in org-private storage, are deduplicated against live capture, require human approval in the Control Panel before any AI reads them, and that nothing unverified is parsed. It also discloses the owner/admin seat requirement and the max 20 files / 200MB limits. What it omits is failure behavior — what happens on hash mismatch at finalize or on an expired signed slot — which matters for a multi-step upload protocol.

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?

The content is front-loaded and every clause carries substantive information about the ingestion protocol rather than filler. The first sentence is overloaded, packing source types, staging behavior, and the pipeline into one long construction, and the later 'nothing unverified is parsed' slightly restates the approval guarantee. Dense but disciplined.

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?

For a nine-parameter, three-action tool with no output schema, the description is unusually complete about the surrounding workflow and guardrails. The gap is return values: it says request 'mints signed upload slots' but never characterizes what runs or finalize hand back, which an agent needs to drive the sequence. Given no output schema exists, that burden falls on the description.

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

Parameters4/5

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

Schema coverage is 89%, so the baseline is 3, and the description adds real value on top: it ties files and consent_version to the request action, run_id and sha256 to finalize, and explicitly notes brain 'never grants access' — a non-obvious semantic about an optional parameter that the schema wording only partly conveys. The session_id and continuity_token parameters are left entirely to their schema text, which is a minor gap.

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 concrete verb and resource — importing history into the org's brain — and enumerates exactly which artifact types qualify (vendor zips, transcripts, IDE/CLI session DBs, note exports) while distinguishing the outcome from sibling wiki tools by noting items 'stage verbatim as wiki candidates.' An agent can tell this is the ingestion path, not the wiki-reading path, 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 Guidelines4/5

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

The description lays out the full call sequence — request mints slots, each file PUTs to signedUrl, then finalize with run_id and sha256, with runs to inspect state — so an agent knows which action to reach for at each step. It also states the prerequisite that consent_version is only valid with the user's explicit go-ahead. It stops short of naming conditions under which an agent should pick a different sibling tool, but no direct alternative exists in the catalog.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources