Sourcey

Get changes

get_changes

Read-onlyIdempotent

Track added, changed, withdrawn, and removed startup credits, discounts, free tiers, perks, and deals through Sourcey's signed change feed after an optional cursor.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cursor`	No	Opaque signed cursor returned by the previous change-feed page.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`release_id`	Yes
`diff_digest`	Yes
`next_cursor`	Yes
`snapshot_id`	Yes
`feed_contract`	Yes
`retained_from_release_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 1, 2026
- addedOutput schema / properties / data / items / properties / tombstone / properties / canonical_route / format
```
Added value: +"starts_with"
```

Changed1 schema field changedSep 28, 2026

changedOutput schema / properties / data / items / properties / kind / examples

Previous value: -[
-  "entity.added",
-  "entity.updated",
-  "entity.retired",
-  "program.added",
-  "program.updated",
-  "program.retired",
-  "offer.added",
-  "offer.updated",
-  "offer.ended",
-  "offer.retired",
-  "offer.withdrawn",
-  "policy.added",
-  "policy.updated",
-  "policy.retired",
-  "agent-readiness.added",
-  "agent-readiness.updated",
-  "agent-readiness.regraded",
-  "agent-readiness.ended",
-  "agent-readiness.withdrawn",
-  "asset.bound",
-  "asset.updated",
-  "asset.withdrawn"
-]New value: +[
+  "entity.added",
+  "entity.updated",
+  "entity.retired",
+  "program.added",
+  "program.updated",
+  "program.retired",
+  "offer.added",
+  "offer.updated",
+  "offer.ended",
+  "offer.retired",
+  "offer.withdrawn",
+  "policy.added",
+  "policy.updated",
+  "policy.retired",
+  "agent-readiness.added",
+  "agent-readiness.updated",
+  "agent-readiness.regraded",
+  "agent-readiness.relocated",
+  "agent-readiness.ended",
+  "agent-readiness.withdrawn",
+  "asset.bound",
+  "asset.updated",
+  "asset.withdrawn"
+]

Changed2 schema fields changedAug 5, 2026

changedOutput schema / properties / data / items / properties / kind / examples

Previous value: -[
-  "entity.added",
-  "entity.updated",
-  "entity.retired",
-  "program.added",
-  "program.updated",
-  "program.retired",
-  "offer.added",
-  "offer.updated",
-  "offer.ended",
-  "offer.retired",
-  "offer.withdrawn",
-  "policy.added",
-  "policy.updated",
-  "policy.retired",
-  "adoption.added",
-  "adoption.updated",
-  "adoption.regraded",
-  "adoption.ended",
-  "adoption.withdrawn",
-  "asset.bound",
-  "asset.updated",
-  "asset.withdrawn"
-]New value: +[
+  "entity.added",
+  "entity.updated",
+  "entity.retired",
+  "program.added",
+  "program.updated",
+  "program.retired",
+  "offer.added",
+  "offer.updated",
+  "offer.ended",
+  "offer.retired",
+  "offer.withdrawn",
+  "policy.added",
+  "policy.updated",
+  "policy.retired",
+  "agent-readiness.added",
+  "agent-readiness.updated",
+  "agent-readiness.regraded",
+  "agent-readiness.ended",
+  "agent-readiness.withdrawn",
+  "asset.bound",
+  "asset.updated",
+  "asset.withdrawn"
+]

changedOutput schema / properties / data / items / properties / subject_type / enum

Previous value: -[
-  "entity",
-  "program",
-  "offer",
-  "policy",
-  "adoption_profile",
-  "asset_binding"
-]New value: +[
+  "entity",
+  "program",
+  "offer",
+  "policy",
+  "agent_readiness_profile",
+  "asset_binding"
+]

Changed1 schema field changedAug 4, 2026
- addedInput schema / properties / cursor / description
```
Added value: +"Opaque signed cursor returned by the previous change-feed page."
```

Changed5 schema fields changedJul 30, 2026

addedOutput schema / properties / data / items / properties / kind / description

Added value: +"Append-only release change kind. Known values are examples; new kinds may appear within public API v1."

removedOutput schema / properties / data / items / properties / kind / enum

Removed value: -[
-  "entity.added",
-  "entity.updated",
-  "entity.retired",
-  "program.added",
-  "program.updated",
-  "program.retired",
-  "offer.added",
-  "offer.updated",
-  "offer.ended",
-  "offer.withdrawn",
-  "policy.added",
-  "policy.updated",
-  "policy.retired",
-  "adoption.added",
-  "adoption.updated",
-  "adoption.regraded",
-  "adoption.ended",
-  "adoption.withdrawn",
-  "asset.bound",
-  "asset.updated",
-  "asset.withdrawn"
-]

addedOutput schema / properties / data / items / properties / kind / examples

Added value: +[
+  "entity.added",
+  "entity.updated",
+  "entity.retired",
+  "program.added",
+  "program.updated",
+  "program.retired",
+  "offer.added",
+  "offer.updated",
+  "offer.ended",
+  "offer.retired",
+  "offer.withdrawn",
+  "policy.added",
+  "policy.updated",
+  "policy.retired",
+  "adoption.added",
+  "adoption.updated",
+  "adoption.regraded",
+  "adoption.ended",
+  "adoption.withdrawn",
+  "asset.bound",
+  "asset.updated",
+  "asset.withdrawn"
+]

addedOutput schema / properties / data / items / properties / kind / pattern
```
Added value: +"^[a-z][a-z0-9-]*(?:\\.[a-z][a-z0-9-]*)+$"
```
addedOutput schema / properties / data / items / properties / kind / x-sourcey-extensible-enum
```
Added value: +true
```

First observedJul 30, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds that the feed is 'signed' (an authenticity/trust property not visible in annotations) and that the cursor is optional, but it does not describe ordering, page size, or how the feed terminates.

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?

One dense sentence with the action and scope front-loaded; the enumerated resource list is long but conveys what is tracked. No redundant or filler content.

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?

With annotations covering the safety profile and an output schema describing return values, the description only needs to establish the change-feed purpose and cursor mechanics, which it does. Missing minor operational details (ordering, pagination termination) keeps it from a 5.

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 coverage is 100% and the single parameter is fully documented in the schema as an opaque signed cursor. The description only echoes that the cursor is optional, adding no syntax or format detail beyond the schema, so the baseline 3 is appropriate.

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

Purpose4/5

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

States a concrete verb (track) and resource (added/changed/withdrawn/removed offers in Sourcey's signed change feed), which is clearly distinct from sibling search_offers and compare_offers. It does not explicitly name which sibling to use instead, but the change-feed framing is unambiguous enough for selection.

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

Usage Guidelines3/5

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

The phrase 'after an optional cursor' implies the pagination workflow (call, then feed the returned cursor back in for the next page), which is useful implied usage. However, there is no explicit statement of when to use this versus the sibling search tools or any preconditions for the first call.

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

All Sourcey tools Inspect

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.