SameDayDesk agent tools
RemoteAbout SameDayDesk agent tools
SameDayDesk agent tools is a set of public helpers for agents, covering free discovery, offline result reuse, and routing tasks to existing offers. It includes offline fixtures and live catalog reads, while documenting capability limits and unavailable acquisition paths.
Key features
- 01Read offline fixtures or free live catalogs
- 02Preview and export result-reuse records
- 03Route tasks using a capability matrix
- 04Use alternate endpoints when cold-read connections fail
Use cases
- 01Check a service catalog without network access
- 02Turn an existing result into a task-memory observation
- 03Check for an available offer before purchasing
- 04Review task-acquisition capabilities and limits
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://samedaydesk.com/mcpclaude mcp add --transport http com-samedaydesk-task-evidence https://samedaydesk.com/mcp{"mcpServers":{"com-samedaydesk-task-evidence":{"type":"http","url":"https://samedaydesk.com/mcp"}}}Open in Cursor{"servers":{"com-samedaydesk-task-evidence":{"type":"http","url":"https://samedaydesk.com/mcp"}}}Open in VS Code{"mcpServers":{"com-samedaydesk-task-evidence":{"type":"http","url":"https://samedaydesk.com/mcp"}}}{"mcpServers":{"com-samedaydesk-task-evidence":{"serverUrl":"https://samedaydesk.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
7| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | The website to check, e.g. example.com or https://example.com |
Details
From the project READMESameDayDesk (public entry)
Public helpers for free discovery and offline result reuse. Node 22.x. The commands below use plain ESM under tools/; no npm install is required.
Start with the examples below, then open the helper documentation for options and error handling.
Docs (in-repo)
| Doc | Purpose |
|---|---|
| tools/presence/FOR-AGENTS-COLD-READ.md | Free discovery when apex TLS/connect fails |
| tools/presence/REGISTRY-CONSUMER.md | MCP Registry version=latest pitfall |
| tools/result-reuse/README.md | Offline source → task-memory observation |
| tools/offer-routing/README.md | Task → existing SameDayDesk/Neomorphic offer |
| tools/offer-routing/capability-limits-matrix.json | Machine-readable capability/limits matrix |
Live free catalogs (no pay): https://agents.samedaydesk.com/llms.txt and https://agents.samedaydesk.com/.well-known/skills/index.json. Apex https://samedaydesk.com/for-agents may TLS/connect-fail; cold-read falls back to those alternates.
Free / live vs offline fixtures
| Mode | Network | Payment | How |
|---|---|---|---|
| Offline fixture cold-read | none | none | preferFixture: true → outcome: "offline_fixture" |
| Live cold-read | free HTTP only | none | default resolve → often alternate_live when apex fails |
| Result-reuse preview/export | none (local JSON) | none | fixtures + --opt-in to write |
These helpers do not require a purchase. Paid extract/batch routes are separate.
Exact commands (clean checkout)
From the repository root (no install):
1. Offline cold-read (no network)
node --input-type=module -e 'import {resolveForAgentsColdRead} from "./tools/presence/for-agents-cold-read.mjs"; console.log(JSON.stringify(await resolveForAgentsColdRead({preferFixture:true}), null, 2))'
Expected: outcome: "offline_fixture", paid: false, liveObserved: false.
2. Live cold-read (free HTTP only; optional)
node --input-type=module -e 'import {resolveForAgentsColdRead} from "./tools/presence/for-agents-cold-read.mjs"; console.log(JSON.stringify(await resolveForAgentsColdRead(), null, 2))'
Expected when apex transport fails but agents.* respond: outcome: "alternate_live", paid: false.
3. Result-reuse preview and export on in-repo fixtures
PILOT_EXAMPLE_DIR="$(mktemp -d)"
NOW="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
node tools/result-reuse/cli.mjs preview \
--input tools/result-reuse/fixtures/accepted-page-change.json \
--task-id vendor-watch --subject vendor-page-result --sequence 1 --clock "$NOW"
node tools/result-reuse/cli.mjs export \
--input tools/result-reuse/fixtures/accepted-page-change.json \
--task-id vendor-watch --subject vendor-page-result --sequence 1 --clock "$NOW" \
--opt-in --out "$PILOT_EXAMPLE_DIR/reuse-observation.json"
printf 'Saved example in %s\n' "$PILOT_EXAMPLE_DIR"
Record-kind fixture:
PILOT_EXAMPLE_DIR="$(mktemp -d)"
NOW="$(date -u +%Y-%m-%dT%H:%M:%SZ)"
node tools/result-reuse/cli.mjs export \
--input tools/result-reuse/fixtures/accepted-record-report.json \
--task-id vendor-watch --subject record-export --sequence 1 --clock "$NOW" \
--opt-in --out "$PILOT_EXAMPLE_DIR/reuse-record-observation.json"
printf 'Saved example in %s\n' "$PILOT_EXAMPLE_DIR"
Expected written observation: schema: "neomorphic.task-memory.observation.v1"; export requires --opt-in plus caller clock/task/subject/sequence.
Task → existing offer (cold selection)
When the job is known, route with the matrix before paying or treating a sample as live:
node tools/offer-routing/route-job.mjs tools/offer-routing/fixtures/complete-issue-discussion.job.json
Expected: ok: false, selected: null, exit code 2 and
complete_issue_acquisition_unavailable. Neither paid /extract nor task-kit
packaging acquires a complete discussion. This matrix does not advertise the
pending issue-evidence acquisition pack. For historical fixture composition use
fixtures/supplied-issue-brief.job.json under tools/offer-routing/.
The MoltJobs SDK pack runs a disposable local HTTP rehearsal; its shipped runner
refuses --live, even with credentials. Hosted archives are downloads, not hosted
job execution. Routing does not evaluate acceptance criteria or authorize payment.
Verify the cited examples
npm run test:public-entry
That script runs the offline cold-read and fixture export commands cited above (no network, no payment). Existing focused suites: npm run test:presence, npm run test:result-reuse, npm run test:offer-routing.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.