Deference MCP
Give your agentits own budget.
One command. One sign-in.
Add the server, approve it in the browser. No key to paste, nothing to install.
Setup guideclaude mcp add --transport http --scope user deference https://deference.si/api/mcp
claude mcp login deferencecodex mcp add deference --url https://deference.si/api/mcp
codex mcp login deference{
"mcpServers": {
"deference": {
"url": "https://deference.si/api/mcp"
}
}
}{
"servers": {
"deference": {
"type": "http",
"url": "https://deference.si/api/mcp"
}
}
}https://deference.si/api/mcp{
"mcpServers": {
"deference": {
"httpUrl": "https://deference.si/api/mcp"
}
}
}{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"deference": {
"type": "remote",
"url": "https://deference.si/api/mcp"
}
}
}{
"context_servers": {
"deference": {
"url": "https://deference.si/api/mcp"
}
}
}{
"mcpServers": {
"deference": {
"type": "streamableHttp",
"url": "https://deference.si/api/mcp",
"disabled": false,
"autoApprove": []
}
}
}extensions:
deference:
name: Deference
type: streamable_http
uri: https://deference.si/api/mcp
enabled: true
timeout: 300Access that renews itself
Approve once. Access refreshes automatically, including during headless runs.
It checks before it spends.
Your agent checks credit, prices and spending before running a model.
What it can do> tidy the build script, then split the test step
● Read package.json, scripts/build.mjs
● Edited scripts/build.mjs (+12 −4)
● Bash npm run build
└ built in 38s, 0 warnings
Build tidied. Lint and tests now run side by side.
> How much can you spend?
deferencedeference_get_balance
└ credit $42.10 · budget $8.40 of $10
$42.10 credit. This connection has $8.40 left.
>
> tidy the build script, then split the test step
● Read package.json, scripts/build.mjs
● Edited scripts/build.mjs (+12 −4)
● Bash npm run build
└ built in 38s, 0 warnings
Build tidied. Lint and tests now run side by side.
> How much can you spend?
deferencedeference_get_balance
└ credit $42.10 · budget $8.40 of $10
$42.10 credit. This connection has $8.40 left.
> Find a model for a 100k-token review under $1.
deferencedeference_list_models
└ 3 models fit · sorted by price
Three fit. The lowest price is $0.31 for this review; the strongest is $0.88.
>
> tidy the build script, then split the test step
● Read package.json, scripts/build.mjs
● Edited scripts/build.mjs (+12 −4)
● Bash npm run build
└ built in 38s, 0 warnings
Build tidied. Lint and tests now run side by side.
> How much can you spend?
deferencedeference_get_balance
└ credit $42.10 · budget $8.40 of $10
$42.10 credit. This connection has $8.40 left.
> Find a model for a 100k-token review under $1.
deferencedeference_list_models
└ 3 models fit · sorted by price
Three fit. The lowest price is $0.31 for this review; the strongest is $0.88.
> Get a second opinion on this diff.
deferencedeference_run_model
└ anthropic/claude-sonnet-5.5 · $0.0042
Done. 3 issues found. Cost $0.0042, $8.39 left.
>
> tidy the build script, then split the test step
● Read package.json, scripts/build.mjs
● Edited scripts/build.mjs (+12 −4)
● Bash npm run build
└ built in 38s, 0 warnings
Build tidied. Lint and tests now run side by side.
> How much can you spend?
deferencedeference_get_balance
└ credit $42.10 · budget $8.40 of $10
$42.10 credit. This connection has $8.40 left.
> Find a model for a 100k-token review under $1.
deferencedeference_list_models
└ 3 models fit · sorted by price
Three fit. The lowest price is $0.31 for this review; the strongest is $0.88.
> Get a second opinion on this diff.
deferencedeference_run_model
└ anthropic/claude-sonnet-5.5 · $0.0042
Done. 3 issues found. Cost $0.0042, $8.39 left.
> What did you spend this week?
deferencedeference_get_usage
└ 247 requests · $4.11
$4.11 across 247 requests. Most went to one model.
>
Models priced for the task
Lists models by price and context, and estimates cost first.
Knows what it has left
Each connection starts at $10 and checks before paid calls.
Every paid call has a ceiling.
Each paid call carries a cost cap and an idempotency key. Retries never charge twice.
Spend budgetSpend, read back by app
Read spend by connection, model and key over 90 days.
Refused before it costs more
$0.50 default, $5 maximum. Higher worst cases are refused.
One charge per idempotency key
Same key and inputs? The retry gets the first receipt.
Keys it makes, limits you set.
Your agent creates, rotates and revokes keys. Limits start at $10, never above $100.
Limits on agent keysAgent keys, tagged and capped
You raise a limit or remove a key here.
You decide what it touches.
Reading is always on. Spending and key management take one switch. Pause or disconnect anytime.
AgentsEvery app in one list
See each connection's permissions, spend and last use.
One switch for spending
Write lets the app run models and manage its keys.
What stays with you
The agent never adds credit or raises its own limits.
Every call, on record.
Each tool call and model request lands in Activity with app, model, tokens and cost.
Activity