Skip to main content
Glama

delimit_secret_store

Store credentials in a scoped, audited secrets broker so agents can retrieve them at runtime with access logging.

Instructions

Write a credential into the Delimit secrets broker store.

When to use: when onboarding an API key, OAuth token, or other credential that one or more agents/tools will need at execution time, and you want the access scoped + audit-logged rather than sitting in an environment variable or .env file. Typical pairing: call this once at setup, then call delimit_secret_get from the consuming tool at runtime. When NOT to use: to fetch the value (use delimit_secret_get for just-in-time access with audit), to inspect which secrets exist without revealing values (delimit_secret_list), to disable an existing secret (delimit_secret_revoke), or to read the access audit trail (delimit_secret_access_log). Also: do not use this as a general-purpose key/value store — the broker is credential- scoped and the audit log will fill up with non-credential noise.

Sibling contrast: delimit_secret_store writes; delimit_secret_get reads with JIT access logging; delimit_secret_list shows metadata only (never values); delimit_secret_revoke disables; together they form the broker surface. Compared to writing a value directly to .env, this routes through a scoped, audited broker.

Side effects: invokes ai.secrets_broker.store_secret which persists the value to the broker's at-rest store. The scope field is also persisted and is enforced on every subsequent delimit_secret_get call. There is no append-only history of stored values — a re-store with the same name overwrites. No network egress and no ledger write; the audit trail is the broker's own access log (visible via delimit_secret_access_log), which records the WRITE event as well as later reads.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoSecret name (key). Required.
valueNoSecret value (the actual credential). Required.
scopeNoComma-separated agent/tool scopes that may access this secret, or "all" to allow any. Default "all".all
descriptionNoHuman-readable description for audit trails.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

No annotations provided, so the description fully covers behavioral traits: persistence, scope enforcement, overwrite behavior, no append-only history, no network egress, and audit trail recording. Discloses internal component invocation.

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?

Well-structured with clear sections (summary, when to use/not, sibling contrast, side effects). Front-loaded with a one-sentence purpose. Slightly verbose but each sentence adds value.

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

Completeness5/5

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

Comprehensively covers all aspects: purpose, usage guidelines, side effects, and parameter semantics. Contrasts with siblings. No gaps given the tool's complexity and absence of annotations.

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?

Input schema has 100% description coverage. The description adds context about scope enforcement and purpose of parameters, enhancing understanding beyond schema alone.

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?

The description explicitly states 'Write a credential into the Delimit secrets broker store,' providing a clear verb and resource. It differentiates from siblings like delimit_secret_get, delimit_secret_list, and delimit_secret_revoke.

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?

Includes explicit 'When to use' and 'When NOT to use' sections, detailing typical scenarios (onboarding API keys) and exclusions (fetching, listing, revoking, general KV store). Also suggests pairing with delimit_secret_get.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/delimit-ai/delimit-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server