Tookan MCP by usefulapi
REMOTE · TOOKAN.USEFULAPI.IO
Read Tookan tasks, agents, teams and customers; create delivery tasks and assign agents.
Available components
Last scanned (1 hour ago)
Scores higher than 47% of remote servers
Reachable. Last reached 17 Oct 2026.
Category Workflow Automation
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security78
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token. View diagnostics → Pass
- HTTPS enforcement could not be verified: the plaintext port redirected somewhere other than https, so enforcement is unproven. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server offers only Dynamic Client Registration (RFC 7591), which MCP 2026-07-28 deprecated in favour of Client ID Metadata Documents. View diagnostics → Partial
Transport & Reachability0
- Transport check failed: declared streamable-http, but the endpoint redirected instead of responding directly. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability78
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2397 tokens (~159/item across 15 items; 15 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 15 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 16 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 17 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +2
- The server rewrote its instructions, which are the text every model session reads security
- The server now declares the “prompts” capability functional
- First check of Schema quality: 100 functional
- New prompt “getting_started” functional
- Server version: 1.4.0 → 1.5.0 functional
- 13 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
- Stability: unverified → 0.07 ▲ functional
- 10 Oct 26 59
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 17 Oct 2026 · Probed https://tookan.usefulapi.io/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=usefulapi.io | CN=WE1,O=Google Trust Services,C=US | 13 Sept 2026 | 12 Dec 2026 | ECDSA 256 | ECDSA-SHA256 | d9be3287b0fde9630e825ba1f79bff3f |
| SANs: usefulapi.io, *.usefulapi.io | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tookan.usefulapi.io. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| io. | present | 57355 | 8 | Verified |
| usefulapi.io. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On tool calls |
| HTTP status | 302 |
WWW-Authenticate challenge Bearer realm="OAuth", resource_metadata="https://tookan.usefulapi.io/.well-known/oauth-protected-resource/mcp"
Bearer realm="OAuth", resource_metadata="https://tookan.usefulapi.io/.well-known/oauth-protected-resource/mcp"Protected resource metadata
| Document | https://tookan.usefulapi.io/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://tookan.usefulapi.io/mcp |
| Authorisation server | https://tookan.usefulapi.io |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://tookan.usefulapi.io/mcp | Redirected | 302 | https://usefulapi.io/tookan/ |
| http (plaintext) | http://tookan.usefulapi.io/mcp | Inconclusive | 302 | http://tookan.usefulapi.io/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
assign_agent_to_task Assign an agent to a task ~118
WRITE: assign (or reassign) a task to an agent of a team; replaces any previous agent. Notifies the agent unless notify is false (so repeating the call notifies again). POST /v2/assign_fleet_to_task.
| Name | Type | Req | Description |
|---|---|---|---|
| fleet_id | integer | yes | Agent id (from list_agents). |
| job_id | integer | yes | Task (job) id. |
| notify | boolean | – | Notify the agent (default true). |
| team_id | integer | yes | The agent's team id (from list_teams). |
No output schema declared.
No examples provided.
create_delivery_task Create a delivery task ~368
WRITE: create a delivery task (job) for a customer address, due by job_delivery_datetime in the given timezone. Optionally assign it to an agent (fleet_id) or team, or let Tookan auto-assign it within the team. Returns job_id and tracking link. Always uses the address given here, not one saved for the customer's phone (ignore_customer_lat_long 1). POST /v2/create_task (has_pickup 0, has_delivery 1, layout_type 0).
| Name | Type | Req | Description |
|---|---|---|---|
| auto_assignment | boolean | – | Let Tookan auto-assign the task to an agent of team_id. |
| customer_address | string | yes | Delivery address. |
| customer_email | string | – | Customer email. |
| customer_phone | string | – | Customer phone, e.g. "+12015555555". |
| customer_username | string | – | Customer name. |
| fleet_id | integer | – | Agent to assign the task to (from list_agents). |
| job_delivery_datetime | string | yes | Deliver before this local time, YYYY-MM-DD HH:MM:SS. |
| job_description | string | – | What is to be delivered. |
| latitude | string | – | Delivery latitude (else Tookan geocodes the address). |
| longitude | string | – | Delivery longitude. |
| notify | boolean | – | Send the customer/agent notifications. |
| order_id | string | – | Your own reference for the task. |
| tags | string | – | Comma-separated agent tags used by auto-assignment. |
| team_id | integer | – | Team to put the task in (from list_teams). |
| timezone | integer | yes | Minutes to ADD to local time to get UTC (Tookan's convention): IST = -330, CET = -60, EST = 300, PST = 480. |
No output schema declared.
No examples provided.
find_customer_by_phone Find customer by phone ~51
Find customers by exact phone number. POST /v2/find_customer_with_phone.
| Name | Type | Req | Description |
|---|---|---|---|
| phone | string | yes | Phone number, e.g. "9897416008" or "+19897416008". |
No output schema declared.
No examples provided.
get_account Get account ~41
The connected Tookan account (admin user): user_id, email, name, company name and address. Good first call. POST /v2/get_user_details.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_agent Get agent profile ~73
One agent's profile (name, email, phone, tags, transport, location, rating, active state) and current tasks. Only profile fields are returned; app tokens and password hashes never are. POST /v2/view_fleet_profile.
| Name | Type | Req | Description |
|---|---|---|---|
| fleet_id | integer | yes | Agent id (fleet_id from list_agents). |
No output schema declared.
No examples provided.
get_agent_location Get agent location ~45
An agent's last known coordinates (latitude/longitude). POST /v2/get_fleet_location.
| Name | Type | Req | Description |
|---|---|---|---|
| fleet_id | integer | yes | Agent id (fleet_id from list_agents). |
No output schema declared.
No examples provided.
get_customer Get customer profile ~42
One customer's profile (contact details, address, coordinates). POST /v2/view_customer_profile.
| Name | Type | Req | Description |
|---|---|---|---|
| customer_id | integer | yes | Customer id (from list_customers). |
No output schema declared.
No examples provided.
get_task_stats Task statistics ~188
Task counts per status (e.g. successful vs failed), optionally for one task type, one team and a date range. Task status codes: 0 assigned, 1 started, 2 successful, 3 failed, 4 in progress/arrived, 6 unassigned, 7 accepted/acknowledged, 8 declined, 9 cancelled, 10 deleted. POST /v2/user_task_stats.
| Name | Type | Req | Description |
|---|---|---|---|
| end_date | string | – | End date, YYYY-MM-DD. |
| job_status | array | – | Only these statuses, e.g. [2, 3]. |
| job_type | – | – | Task type: 0 = pickup, 1 = delivery, 2 = appointment, 3 = field workforce (FOS). |
| start_date | string | – | Start date, YYYY-MM-DD. |
| team_id | integer | – | Only tasks of this team. |
No output schema declared.
No examples provided.
get_tasks Get task details ~166
Full details of up to 100 tasks by job id: customer, addresses, agent (fleet_id/fleet_name), status, timestamps (started/arrived/completed), tracking link, custom fields; optionally the status history. Task status codes: 0 assigned, 1 started, 2 successful, 3 failed, 4 in progress/arrived, 6 unassigned, 7 accepted/acknowledged, 8 declined, 9 cancelled, 10 deleted. POST /v2/get_job_details.
| Name | Type | Req | Description |
|---|---|---|---|
| include_additional_info | boolean | – | Include the job's additional info. |
| include_task_history | boolean | – | Include each task's status history. |
| job_ids | array | yes | Task (job) ids, e.g. [5145]. |
No output schema declared.
No examples provided.
get_tasks_by_order_id Get tasks by order id ~76
Full details of the tasks carrying the given order ids (the reference you set when creating a task). POST /v2/get_job_details_by_order_id.
| Name | Type | Req | Description |
|---|---|---|---|
| include_task_history | boolean | – | Include each task's status history. |
| order_ids | array | yes | Order ids, e.g. ["P000469"]. |
No output schema declared.
No examples provided.
list_agents List agents ~247
List agents (drivers / field workers; Tookan calls them fleets) with fleet_id, name, phone, tags, team and live status (0 available, 1 offline, 2 busy). Filter by name, tags, availability or fleet ids. The API returns the whole list; this tool returns a window (limit/offset, next_offset). POST /v2/get_all_fleets.
| Name | Type | Req | Description |
|---|---|---|---|
| fleet_ids | array | – | Only these agent ids. |
| fleet_type | – | – | 1 = captive agents, 2 = freelancers. |
| include_team_id | boolean | – | Include each agent's team id. |
| limit | integer | – | Max items to return (default 50, max 200). |
| match_any_tag | boolean | – | With tags: true = agents having ANY of the tags, false = ALL of them. |
| name | string | – | Only agents whose name matches this text. |
| offset | integer | – | Items to skip (use next_offset from the previous call). |
| status | – | – | 0 = only free agents, 1 = only busy agents. |
| tags | string | – | Comma-separated agent tags, e.g. "mini,suv". |
No output schema declared.
No examples provided.
list_customers List customers ~99
List customers (customer_id, name, phone, email, address), optionally searched by name or phone. Paginated: one Tookan page per call (page, default 1). POST /v2/get_all_customers.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | Search by customer name. |
| page | integer | – | Page number (default 1). Tookan pages are a fixed size. |
| phone | string | – | Search by customer phone number. |
No output schema declared.
No examples provided.
list_tasks List tasks ~404
List tasks (Tookan calls them jobs) of one task type within a date range of the task date (at most 31 days, within the last 31 days). Paginated: one Tookan page per call (page, default 1). Filter by status, agent (fleet_id), team, customer, job ids or your order ids. Task status codes: 0 assigned, 1 started, 2 successful, 3 failed, 4 in progress/arrived, 6 unassigned, 7 accepted/acknowledged, 8 declined, 9 cancelled, 10 deleted. POST /v2/get_all_tasks.
| Name | Type | Req | Description |
|---|---|---|---|
| custom_fields | boolean | – | Include the tasks' custom-field data. |
| customer_id | integer | – | Only tasks of this customer (from list_customers). |
| end_date | string | yes | End of the task-date range, YYYY-MM-DD (at most 31 days after start_date). |
| fleet_id | integer | – | Only tasks of this agent (from list_agents). |
| job_ids | array | – | Only these task (job) ids. |
| job_status | – | – | Only tasks in this status. Task status codes: 0 assigned, 1 started, 2 successful, 3 failed, 4 in progress/arrived, 6 unassigned, 7 accepted/acknowledged, 8 declined, 9 cancelled, 10 deleted. |
| job_type | – | yes | Task type: 0 = pickup, 1 = delivery, 2 = appointment, 3 = field workforce (FOS). |
| order_ids | array | – | Only tasks with these order ids (your own reference). |
| page | integer | – | Page number (default 1). Tookan pages are a fixed size. |
| start_date | string | yes | Start of the task-date range, YYYY-MM-DD. |
| team_id | integer | – | Only tasks of this team (from list_teams). |
No output schema declared.
No examples provided.
list_teams List teams ~116
List teams (team_id, name, address, tags). With include_agents, each team also lists its agents. Returns a window (limit/offset, next_offset). POST /v2/view_all_team_only (or /v2/view_teams with agents).
| Name | Type | Req | Description |
|---|---|---|---|
| include_agents | boolean | – | Also return each team's agents (larger reply). |
| limit | integer | – | Max items to return (default 50, max 200). |
| offset | integer | – | Items to skip (use next_offset from the previous call). |
No output schema declared.
No examples provided.
update_task_status Update task status ~153
WRITE (DESTRUCTIVE): force a task's status, overriding the agent app. Completing (2 successful, 3 failed) or cancelling (9) closes the task and notifies per the account's settings; confirm with the user first. Deleting (10) is not offered. Settable: 0 assigned, 1 started, 2 successful, 3 failed, 4 arrived, 6 unassigned, 7 accepted, 8 declined, 9 cancelled. POST /v2/update_task_status.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | integer | yes | Task (job) id. |
| job_status | – | yes | New status code (0-4, 6-9; 10 deleted is not allowed). |
No output schema declared.
No examples provided.
How do I install the Tookan MCP by usefulapi server?
Tookan MCP by usefulapi is a hosted endpoint at https://tookan.usefulapi.io/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · tookan.usefulapi.io
claude mcp add --transport http io-usefulapi-tookan 'https://tookan.usefulapi.io/mcp'
What is the Tookan MCP by usefulapi server?
Tookan MCP by usefulapi is listed in the public MCP registry as io.usefulapi/tookan. Read Tookan tasks, agents, teams and customers; create delivery tasks and assign agents. This page covers its hosted endpoint (https://tookan.usefulapi.io/mcp).
Is the Tookan MCP by usefulapi server safe to use?
Tookan MCP by usefulapi scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Tookan MCP by usefulapi server expose?
Tookan MCP by usefulapi exposes 15 tools: get_account, list_tasks, get_tasks, get_tasks_by_order_id, get_task_stats, and 10 more. Their descriptions and schemas cost roughly 2,187 tokens of context every time the server is loaded.
Does the Tookan MCP by usefulapi server require authentication?
Yes. Tookan MCP by usefulapi asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Tookan MCP by usefulapi server still maintained?
Tookan MCP by usefulapi is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.