MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description reveals important behaviors beyond annotations: config-based login gives a non-expiring connection, token-based login is session-only, and no-args calls return a login link. This complements the annotations without contradicting them, though it does not detail error conditions or what happens after authentication.
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?
The description is compact and all sentences contribute useful guidance. The structure is a bit dense and some phrasing is awkward, but it front-loads the core instruction and then presents two options clearly.
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?
Given one optional parameter, no output schema, and an uncomplicated auth flow, the description covers both entry points (token vs no-args) and explains the long-term session setup. It does not describe what the tool returns on success/failure, but this is not essential for this simple tool.
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?
With 0% schema description coverage, the description carries the full weight. It clarifies that the token parameter is a JWT and describes usage from the user's perspective. It could add stricter format or expiry details, but is enough for correct invocation.
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?
The description clearly identifies this as the authentication tool for MCP.AI: it tells the agent to have the user log in, copy the access token, and pass it either through configuration or the token parameter. It distinguishes itself from sibling tools like 'connect' by specifying its exact role and the browser/token flow.
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?
Explicit guidance is given for the two modes: permanent login via config header, and session-only login by pasting the token. It also explains calling with no args to get the link, covering the practical decision points. It does not compare itself to sibling tools, but this is not essential for a self-contained authentication flow.
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.
Most tools have distinct purposes (auth, connection status, marketplace, recall card retrieval, search, system info). However, marketplace is a mega-tool with many sub-capabilities that could overlap with toolkit_info or connect in some contexts, creating minor ambiguity.
Naming is inconsistent: some tools use simple verbs (authenticate, connect), some use verb_noun with underscores (report_bug, show_version), and the recall_* tools follow a clear recall_action_noun pattern. This mix of conventions reduces predictability.
10 tools is a reasonable count for the combined domain of Recall knowledge base and MCP marketplace management. Each tool earns its place, though the marketplace tool bundles many operations into one that could be split.
The Recall knowledge base side is missing create, update, and delete card operations, severely limiting lifecycle management. While marketplace capabilities are extensive, the core Recall functionality is incomplete for a CRUD-based domain.