Interact with Microsoft 365 and Office services through the Microsoft Graph API.
SideQuest is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
What it does
Hire verified local people for real-world tasks. Paid upfront, released on approved photo proof.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user uckhill-sidequest-mcp '--' npx -y sidequestpays-mcp
# 2 — ask your agent for something these tools do
# list_templates, create_quest, get_balance and 6 more
SideQuest costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user uckhill-sidequest-mcp '--' npx -y sidequestpays-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Its publisher also runs it at https://sidequestpays.com/mcp: nothing to start on your machine, and this marketplace is not in the path.
claude mcp add --scope user --transport http uckhill-sidequest-mcp https://sidequestpays.com/mcpNothing is required, but it can take X-API-Key header (SideQuest API key. Optional for clients that support OAuth sign-in. Get one with POST /v1/requesters.) if you want to set it.
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
9 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
List the quest types a person can do for you. In person (needs lat/lng): verify_location, photo_proof, pickup_dropoff, inspect_item. Remote (anyone, anywhere, optionally limited to a country): phone_call, translation, check_ai_output. Call this first to pick the right template.
No parameter schema on file.
Post a paid real-world quest for a verified human quester near a location. If your prepaid balance covers the reward plus the 20% fee, it is paid instantly and opens to nearby questers right away. Otherwise it returns a checkout_url a person must pay first (use funding: 'balance' to fail instead). Use for tasks only a person on site can do. Account creation, social media posting, reviews, CAPTCHAs
| Parameter | Type | Required | Notes |
|---|---|---|---|
| template | string | yes | Quest type from list_templates. |
| title | string | yes | Short, clear instruction, e.g. 'Confirm Joe's Hardware at 12 Main St is open and photograph posted hours'. |
| details | object | no | Step-by-step instructions shown to the quester. |
| lat | number | no | Latitude where the quest happens. Required for in-person templates, ignored for remote ones. |
| lng | number | no | Longitude where the quest happens. Required for in-person templates, ignored for remote ones. |
| country | string | no | Optional 2-letter ISO code. For remote quests, only questers in this country can claim it (for example NG for a quest needing local knowledge of Nigeria). |
| language | string | no | Language needed, like Spanish or Yoruba. Required for translation quests. |
| zip | string | no | Optional ZIP or postal code of the quest location. |
| reward_usd | number | yes | What the quester earns. A 20% platform fee (minimum $2) is added on top. |
| funding | string | no | auto (default): use balance if it covers the total, else return a checkout_url. balance: only use balance, error if short. checkout: always return a checkout_url. |
Check your prepaid balance, this key's spend caps, and how much it has spent in the last 24 hours. Call before posting quests to know whether they will be paid instantly.
No parameter schema on file.
Get one of your quests by id, including status and, once submitted, the quester's proof (photo URLs, GPS, timestamp, notes). Photo URLs need the same API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quest_id | string | yes | The quest id returned by create_quest, like q_abc123. |
List your quests, newest first. Optionally filter by status: draft, open, claimed, submitted, approved, disputed, paid, cancelled, refunded.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Only return quests with this status. Omit for all. |
| limit | number | no | Maximum quests to return. Default 50. |
Approve a submitted quest after checking its proof. This releases the secured reward to the quester. Optionally rate the quester 1 to 5. Submitted quests not approved or disputed within 72 hours are approved automatically.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quest_id | string | yes | The quest id returned by create_quest, like q_abc123. |
| rating | number | no | Optional rating of the quester, 1 (poor) to 5 (excellent). |
Dispute a submitted quest whose proof does not meet the instructions. Funds stay held while a SideQuest reviewer decides. Give a specific reason.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quest_id | string | yes | The quest id returned by create_quest, like q_abc123. |
| reason | string | yes | What the proof is missing or got wrong, specific enough for a reviewer to judge. |
Receive signed HTTPS callbacks when your quests change status (quest.opened, quest.claimed, quest.submitted, quest.paid, quest.disputed, quest.released, quest.refunded, quest.cancelled) instead of polling get_quest. Returns a signing secret once.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | Your https endpoint that will receive POSTed quest events. |
Cancel a quest before a quester claims it. Paid quests are refunded in full. Claimed quests cannot be cancelled.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| quest_id | string | yes | The quest id returned by create_quest, like q_abc123. |
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install SideQuest or to call it, at any volume.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Any signed-in account that does not publish SideQuest can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.