flconsole MCP server
On this page
flconsole MCP is a free MCP server for new Upwork jobs: connect it to Claude Code, Codex, Cursor or the Claude app, and your agent finds new jobs, reads them and shows you the ones that fit. New to it? See how to use flconsole with your AI agent four use cases with prompts and the feed tuner, which keeps your Telegram alerts accurate on a schedule. This page is the reference: every tool, argument, filter and limit.
Overview
| Setting | Value |
|---|---|
| Server URL | https://mcp.lite.flconsole.com/mcp |
| Transport | Streamable HTTP |
| Sign-in | Through Telegram: no password, no API key |
| Price | Free |
Search with filters, no feed needed. Your agent passes a search query, job and client filters in each
find_jobscall. The server returns jobs posted in the last 30 minutes; there is no search in older jobs.Your agent is the AI filter. Filters are structured JSON. Picking jobs by meaning, by your criteria in plain words, is done by your agent, not by the server.
Your agent asks; the server doesn't push. The agent checks for new jobs when you ask it or on a schedule. For alerts within a minute of posting, use the Telegram bot.
One feed, two modes. A feed is a saved search with an alerts switch: alerts off — for your agent only; alerts on — the Telegram bot also sends you every new matching job. Both kinds show up in the bot under
/feeds.No access to your Upwork account. flconsole never asks for your Upwork login and can't act in your account.
Three ways to work
| Way | What your agent does | What is stored |
|---|---|---|
| 1. Search only | Passes a search query and filters in each call | Nothing |
| 2. Feeds for your agent + memory | Starts each session with your feeds and its notes about you, and keeps them up to date | Up to 5 feeds with alerts off (search, filters, your AI filter, the agent's notes) and the agent's notes about you, on flconsole's server |
| 3. Telegram alerts | Turns on alerts for a feed with one call; the bot sends you every new matching job, filtered by the same AI filter | The same feed, with alerts on |
Way 2 uses get_agent_context at the start of a session, create_feed (alerts off by default) and save_agent_instructions to save, and find_jobs with feed_id or all_feeds to check. Any agent you connect, on any device, gets the same feeds and notes and picks up where the last one stopped. A feed with alerts off sends nothing to Telegram and nothing runs on the server: your agent checks it with find_jobs and applies its AI filter itself. Way 3 is set_feed_alerts: the same feed, now with Telegram alerts.
Connect
Add the server to your client, then sign in. Sign-in works the same way everywhere:
- Your client opens a sign-in page in the browser.
- Tap Continue in Telegram (or scan the QR code with your phone). The flconsole bot opens. If you're new, tap Start — that's all it takes.
- The bot names the app that wants access. Tap Allow, and the bot shows a 4-digit code.
- Enter the code on the sign-in page. Your client is connected.
Step 1: Add the server in your client
claude mcp add --transport http flconsole https://mcp.lite.flconsole.com/mcp
/mcp → flconsole → Authenticate
codex mcp add flconsole --url https://mcp.lite.flconsole.com/mcp
codex mcp login flconsole
Add custom connector
https://mcp.lite.flconsole.com/mcp
Add
"flconsole": { "url": "https://mcp.lite.flconsole.com/mcp" }
MCP settings → flconsole → Connect
Step 2: The sign-in page opens
Connect Claude CodeCodexClaudeCursor to flconsole
Continue in Telegram
Enter the code from Telegram
····
Step 3: Telegram: tap Allow
🔐 Connect Claude CodeCodexClaudeCursor?
App: Claude CodeCodexClaudeCursor
✅ Allow✖ Cancel
Your code: 4821
Step 4: Enter the code: connected
Enter the code from Telegram
4821
Claude CodeCodexClaudeCursor is connectedGo back to Claude CodeCodexClaudeCursor — it's ready.
Claude Code
claude mcp add --transport http flconsole https://mcp.lite.flconsole.com/mcpAdd --scope user to make the server available in all your projects. Then run /mcp in Claude Code, pick flconsole and choose Authenticate.
Step-by-step guide: flconsole in Claude Code.
Skill: upwork-job-hunter
The upwork-job-hunter skill (SKILL.md) sets up the search with you in 3 steps, like the Telegram bot: what to search, job and client filters, and your own criteria, which the agent applies itself. It counts matching jobs with preview_filters at each step, tests your criteria on real jobs, shows a shortlist with reasons on every check and tunes the setup when there are too many jobs, too few or not the right ones.
- Claude Code:
npx skills add droopboop/flconsole-upwork-mcp, or copySKILL.mdinto~/.claude/skills/upwork-job-hunter/. - Claude app, no terminal: download upwork-job-hunter.zip and upload it in Customize → Skills (steps).
Then say: "Set up my Upwork job search."
Codex
codex mcp add flconsole --url https://mcp.lite.flconsole.com/mcp
codex mcp login flconsoleThe second command opens the sign-in page in your browser. Guide: flconsole in Codex.
Claude app
Web, desktop and mobile: Customize → Connectors → + → Add custom connector, then paste https://mcp.lite.flconsole.com/mcp. The app opens the sign-in page. Guide: flconsole in the Claude app.
Cursor
Add the server to ~/.cursor/mcp.json:
{
"mcpServers": {
"flconsole": { "url": "https://mcp.lite.flconsole.com/mcp" }
}
}Then sign in from Cursor's MCP settings when it asks. Guide: flconsole in Cursor.
Other clients
Any MCP client with Streamable HTTP works. If it supports sign-in (OAuth), add the server URL and sign in as above. If it doesn't, use a manual token.
Manual token
For clients without sign-in support. In the Telegram bot, send /mcp and tap Manual token (other apps). The bot shows the token once and doesn't store it, together with ready-to-paste commands.
Send it as a header: Authorization: Bearer <token>.
Claude Code:
claude mcp add --transport http flconsole https://mcp.lite.flconsole.com/mcp \
--header "Authorization: Bearer <token>"Codex, in ~/.codex/config.toml, with the token in an environment variable:
[mcp_servers.flconsole]
url = "https://mcp.lite.flconsole.com/mcp"
bearer_token_env_var = "FLCONSOLE_MCP_TOKEN"export FLCONSOLE_MCP_TOKEN=<token>Tools
The server has 21 tools. The last four run the feed tuner: you turn it on once in a chat, then a scheduled task (for example in Claude, hourly) checks your feeds with alerts and keeps them accurate. The server decides when each feed is due. Every change comes to Telegram with ↩️ Undo.
| Tool | What it does | Limit |
|---|---|---|
get_agent_context | Start of a session: how-to, your agent's notes and all your feeds | None |
get_skill | Loads a detailed how-to (skill) when the agent needs it | None |
find_jobs | New jobs by a feed, all feeds or any filters | 100 jobs an hour, 1,000 a day |
get_job_details | Full data for the jobs you picked | 30 details an hour |
save_agent_instructions | Saves the agent's notes about you: preferences, conclusions | 30 storage changes an hour |
rate_job | Saves your 👍 or 👎 on a job from a feed, when you tell the agent | 30 storage changes an hour |
list_feeds | Your feeds: filters, AI filter, alerts on or off, paused | None |
create_feed | Saves a feed, alerts off by default; needs your approval | 20 changes an hour |
update_feed | Changes a feed's search, filters, AI filter or the agent's notes | 20 changes an hour |
set_feed_alerts | Turns Telegram alerts for a feed on or off; needs your approval | 20 changes an hour |
set_feed_paused | Pauses or resumes a feed | 20 changes an hour |
delete_feed | Deletes a feed; needs your approval | 20 changes an hour |
preview_filters | How many jobs matched over 7 days: total, ~per day and per day, with samples | 10 an hour |
parse_upwork_url | Turns an Upwork search link into filters | 30 an hour |
list_categories | Upwork categories and subcategories | None |
find_locations | Countries and regions by name | None |
get_usage | What's left of your limits | None |
tuner_checkin | Start of a feed tuner run: which feeds are due now | None |
get_feed_report | What a feed sent, your 👍/👎, what the AI filter skipped, recent changes | None |
set_feed_tuner | Turns the feed tuner on or off for a feed; needs your approval | 20 changes an hour |
log_tuner_run | End of a tuner run: what it found and changed; the change comes to Telegram with Undo | 30 storage changes an hour |
find_jobs
Returns new jobs by filters you pass in the call (a search query, job and client filters: no feed needed), from one feed, or from all your feeds. Pass exactly one source: filters, feed_id or all_feeds.
Arguments6
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | No | One feed, alerts on or off |
all_feeds | boolean | No | All your feeds that are not paused |
filters | object | No | Any filters, without a feed |
cursor | string | No | Only with filters: cursor from the previous response |
lookback_minutes | integer | No | Only with filters, without cursor; default and maximum 30 |
limit | integer | No | 1–30, default 10; capped by the remaining quota |
- Each call returns only jobs newer than the previous check, and never jobs older than 30 minutes. Jobs come oldest first, as short cards.
- With
feed_idorall_feeds, the server remembers where each feed stopped, separately for each connection. Each job lists the feeds it matched inmatched_feeds, and the response lists each feed'sai_filterwithapply: "agent": your agent applies it to each job;find_jobsdoesn't. - A paused feed is used by nobody:
feed_idof a paused feed returnsfeed_paused, andall_feedsskips it. - With
filters, nothing is saved. Pass thecursorfrom the response into the next call to get only newer jobs. - With alerts on, the bot applies the same AI filter before each Telegram alert.
- The response also has
skipped_count, yourquotafor the hour and the day, andnext_check_after.
Limit100 jobs an hour, 1,000 a day, one call every 60 seconds
get_agent_context
Call it first in every session. Returns the short main how-to for this server with a list of skills to load with get_skill, the agent's notes about you saved in earlier sessions, all your feeds (alerts on or off, paused, AI filter, the agent's notes) and the feed limits. No arguments.
get_job_details
Full data of jobs returned by find_jobs: experience level, duration, workload, category and client statistics. Use it for the few jobs worth a closer look, not for every job found.
Arguments1
| Argument | Type | Required | What it does |
|---|---|---|---|
upwork_ids | array of strings | Yes | 1–5 upwork_id values from find_jobs |
Every requested job counts toward the quota, including ones that weren't found. Jobs that weren't found are listed in not_found.
Limit30 jobs an hour
get_skill
Returns one detailed how-to by name: job-scout (your agent searches and picks jobs itself, no Telegram), telegram-setup (feeds with Telegram alerts), filter-writing (how to write search, filters and an AI filter), ratings (when to save 👍/👎), feed-tuner (keeps a feed with alerts accurate on a schedule). The list with one line each comes from get_agent_context.
Arguments1
| Argument | Type | Required | What it does |
|---|---|---|---|
name | string | Yes | Skill name from the list |
rate_job
Saves your rating of a job from one of your feeds, the same as the 👍/👎 buttons under a Telegram alert. The agent uses it only when you say you liked or disliked a job, never on its own judgment. After a few 👎 for the same reason the bot suggests how to make the feed sharper.
Arguments5
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Your feed |
job | string | Yes | Job id from find_jobs or an alert |
rating | string | Yes | up or down |
reason | string | For down | skill, budget, client or other |
note | string | No | Up to 300 characters in your words |
Limit30 storage changes an hour
save_agent_instructions
Saves the agent's notes about you: preferences, rates, red flags, proposal style, conclusions of reviews. Any agent you connect later gets them from get_agent_context.
Arguments2
| Argument | Type | Required | What it does |
|---|---|---|---|
text | string | Yes | Up to 6,000 characters in total. With replace, the full new text ("" clears it); with append, only the new part |
mode | string | No | replace (default) or append |
Limit30 storage changes an hour (together with update_feed calls that change only agent_notes)
list_feeds
All your feeds: feed_id, name, alerts (Telegram alerts on or off), paused, filters, a one-line summary, AI filter and the agent's notes. No arguments.
telegram_delivery shows whether Telegram alerts go out: active, paused (this feed is paused), stopped (you sent /stop), blocked (you blocked the bot) or off (alerts are off: the feed is for your agent). The response also has feed_limits: how many feeds with alerts on and off you have and can have.
create_feed
Saves a feed: a search with job and client filters, your AI filter and the agent's notes, to reuse with find_jobs(feed_id). With alerts: false (the default) it is for your agent only: nothing goes to Telegram and nothing runs on the server. With alerts: true the Telegram bot also sends you an alert about every new matching job.
Arguments6
| Argument | Type | Required | What it does |
|---|---|---|---|
filters | object | Yes | Complete filters; base.q is required |
name | string | No | Up to 40 characters; automatic if omitted |
alerts | boolean | No | Telegram alerts; default false |
ai_filter | string | No | AI filter rules in plain words, up to 2,000 characters |
agent_notes | string | No | The agent's notes for this feed, up to 1,500 characters |
user_confirmed | boolean | Yes | true only after you approved saving this feed (and, with alerts: true, asked for Telegram alerts) |
With alerts on, you get a message in Telegram about the new feed.
Limit20 feed changes an hour (create, update, alerts, pause and delete together, for both kinds of feeds)
update_feed
Changes a feed's name, filters, AI filter or the agent's notes. Pass at least one of name, filters, ai_filter, agent_notes.
Arguments7
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Feed id from list_feeds |
filters | object | No | Replaces the saved filters entirely: send the full object |
name | string | No | New name |
ai_filter | string | No | Replaces the AI filter; "" removes it; omit to keep it |
agent_notes | string | No | Replaces the agent's notes, up to 1,500 characters; "" clears them |
user_confirmed | boolean | For feeds with alerts on | true only after you approved this exact change; not needed for agent_notes alone |
run_id | string | Tuner runs only | From tuner_checkin, instead of user_confirmed: search, filters, AI filter and notes, at most 3 edits per run |
For a feed with alerts on, you get a message in Telegram about what changed.
Limit20 feed changes an hour; a call that changes only agent_notes counts as a storage change (30 an hour)
set_feed_alerts
Turns Telegram alerts for a feed on or off. On: the bot sends you every new matching job from now on, filtered by the feed's AI filter; it needs a free place among your 5 feeds with alerts, otherwise feed_limit_reached. Off: the feed stays for your agent only.
Arguments3
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Feed id from list_feeds |
on | boolean | Yes | true turns alerts on, false off |
user_confirmed | boolean | Yes | true only after you asked for this |
You get a message in Telegram. In the bot, the same switch is in the feed card: 🔔 Get alerts here and 🔕 Agent only.
Limit20 feed changes an hour
set_feed_paused
Pauses or resumes a feed. A paused feed sends no alerts, and find_jobs doesn't use it.
Arguments3
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Feed id from list_feeds |
paused | boolean | Yes | true pauses, false resumes |
user_confirmed | boolean | For feeds with alerts on | true only after you approved it |
Limit20 feed changes an hour
delete_feed
Deletes a feed, with alerts on or off.
Arguments2
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Feed id from list_feeds |
user_confirmed | boolean | Yes | true only after you approved deleting this feed |
You get a message in Telegram about the deleted feed.
Limit20 feed changes an hour
preview_filters
How many jobs matched the filters over the last 7 days: the total, about how many a day, and a count for each UTC day, with up to 3 short samples. Use it to check filters before creating a feed or calling find_jobs.
Arguments2
| Argument | Type | Required | What it does |
|---|---|---|---|
filters | object | Yes | Filters to check |
window_hours | integer | No | 1–168, default 168 (7 days) |
Each sample has the title, link, job type, rate or budget, posting time and the client's country, total spent and rating.
Limit10 calls an hour
parse_upwork_url
Turns an Upwork job search link into filters. Open upwork.com/nx/search/jobs, set your search and filters, and copy the address.
Arguments1
| Argument | Type | Required | What it does |
|---|---|---|---|
url | string | Yes | Upwork job search link |
Returns filters, a readable list of them, a suggested feed name and any link parameters that weren't recognized. A link to a single job is not a search link.
Limit30 calls an hour
list_categories
Upwork categories and subcategories with their upwork_id, for base.category2_uid and base.subcategory2_uid. No arguments.
find_locations
Finds countries, subregions and regions by name or alias, for base.location.
Arguments1
| Argument | Type | Required | What it does |
|---|---|---|---|
query | string | Yes | Part of a name, 1–100 characters |
Returns up to 30 matches with type (country, subregion or region), aliases and the region each belongs to.
get_usage
What's left of your hourly and daily quotas, when the next find_jobs is allowed, and your feed counts and limits (alerts on and off). No arguments.
tuner_checkin
Start of every tuner run. For each feed with the tuner on: due, stage, target_band, notes, next_check_at, since and, when due, run_id. Nothing due: the run stops after this one call.
Arguments1
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_ids | array | No | Only these feeds |
No hourly limit.
get_feed_report
What a feed did since a time: jobs sent (count, last 24 hours, recent titles), opened, jobs a day, your 👍/👎 with reasons and notes, ai_skipped (how many jobs the AI filter skipped, with examples and the rule), alerts and pause state, tuner state and recent changes (who changed what: you in the bot, your agent, the tuner).
Arguments2
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Your feed |
since | string | No | ISO 8601 time; default the last tuner run, or 7 days ago |
No hourly limit.
set_feed_tuner
Turns the tuner on or off for a feed with Telegram alerts. Turning it on needs the jobs-a-day band you want and your clear yes in the chat: that yes lets the tuner change this feed within its rules. You get a message in Telegram either way.
Arguments4
| Argument | Type | Required | What it does |
|---|---|---|---|
feed_id | integer | Yes | Your feed |
on | boolean | Yes | true on, false off |
target_band | object | For on: true | Jobs a day, e.g. {"min": 5, "max": 15} |
user_confirmed | boolean | For on: true | true only after you agreed to the tuner on this feed |
Limit20 feed changes an hour
log_tuner_run
End of a tuner run for one feed, also when nothing changed. If the feed changed, change and reason come to you in Telegram word for word, with ↩️ Undo.
Arguments6
| Argument | Type | Required | What it does |
|---|---|---|---|
run_id | string | Yes | From tuner_checkin |
feed_id | integer | Yes | Your feed |
findings | string | Yes | Notes for the next run; not shown to you |
reason | string | Yes | Why, in one plain sentence |
change | string | No | What changed, in one plain sentence |
open_question | string | No | What to ask you next time you chat |
Limit30 storage changes an hour
Filters
create_feed, update_feed, preview_filters and find_jobs take the same filters object:
{
"schema_version": 1,
"base": {
"q": "elevenlabs OR vapi OR retell",
"t": ["hourly"],
"hourly_rate": { "min": 40, "max": null },
"contractor_tier": ["expert"],
"location": { "include": ["United States", "Western Europe"], "exclude": [] },
"payment_verified": true
},
"advanced": {
"cl_total_spent": { "min": 10000, "max": null },
"cl_rating": { "min": 4.5, "max": null }
}
}schema_versionis required and is always1.- A key that is omitted,
nullor[]is not set. Yes/no filters taketrue,falseornull(any). - Ranges are
{ "min": …, "max": … }; either side can benull. - Unknown keys are rejected with
invalid_filters, so a typo never silently filters nothing. - Client filters: a client without that statistic doesn't match a range.
base
All base keys13
| Key | Type | What it filters |
|---|---|---|
q | string | Search query, required. See search syntax |
category2_uid | array of strings | Categories: upwork_id from list_categories |
subcategory2_uid | array of strings | Subcategories: upwork_id from list_categories |
t | array | Job type: hourly, fixed |
contractor_tier | array | Experience level: entry, intermediate, expert |
amount | range | Fixed budget, $ |
hourly_rate | range | Hourly rate, $ |
client_hires | array of ranges | Client's number of hires; any of the ranges |
workload | array | Hours per week: less_than_30_hours, more_than_30_hours |
duration_v3 | array | Project length: less_than_one_month, 1_to_3_months, 3_to_6_months, more_than_6_months |
contract_to_hire | boolean | Contract-to-hire jobs |
location | object | include and exclude: country, subregion or region names from find_locations |
payment_verified | boolean | Client's payment method verified |
A job matches if it is in any of the listed categories or subcategories.
advanced
All advanced keys17
| Key | Type | What it filters |
|---|---|---|
cl_total_spent | range | Client's total spent, $ |
cl_rating | range | Client's rating, 0–5 |
cl_review_cnt | range | Number of reviews |
cl_hire_rate | range | Hire rate, % |
cl_registered_at | object | Account age: max_days_ago: 1095 = older than 3 years; min_days_ago: 30 = newer than 30 days |
cl_avg_hourly | range | Average hourly rate paid, $ |
cl_paid_hours | range | Hours paid |
cl_posted_jobs_cnt | range | Jobs posted |
cl_open_jobs_cnt | range | Open jobs |
cl_hires_cnt | range | Hires |
cl_active_hires_cnt | range | Active hires |
cl_work_history_cnt | range | Jobs in work history |
cl_avg_spent_per_hire | range | Total spent divided by hires, $ |
cl_phone_verified | boolean | Phone verified |
cl_enterprise | boolean | Enterprise client |
has_questions | boolean | Job has screening questions |
has_attachments | boolean | Job has attachments |
Search syntax
base.q works like the search box on Upwork:
react native both words
"voice agent" exact phrase
vapi OR retell any of them
python NOT wordpress exclude a word- At least 3 letters: a shorter search matches almost every job.
- Not only exclusions:
NOT wordpressalone is rejected. Add words to look for. - Up to 1,000 characters. Parentheses group terms:
(vapi OR retell) AND voice. - Search in English: Upwork jobs are posted in English.
- Upwork search can't read field names like
skills:, the characters/ [ ] ~, or*at the start of a word. Such a query is rejected withinvalid_query. - Rates, locations and client requirements belong in filters, not in the search.
Job fields
find_jobs returns short cards: enough to judge a job by its text. get_job_details adds the terms and the client's history.
| Field | Short card | Full details |
|---|---|---|
upwork_id, link, title | Yes | Yes |
description | Up to 5,000 characters, with description_truncated | Full text |
skills | Yes | Yes |
job_type, hourly_rate_from, hourly_rate_to, fixed_budget | Yes | Yes |
publish_at | Yes | Yes |
matched_feeds | With feed_id or all_feeds | None |
experience_level, project_length, workload, contract_to_hire | None | Yes |
has_questions, has_attachments, category | None | Yes |
client.country | Yes | Yes |
| Other client data | None | City, payment and phone verified, enterprise, rating, reviews, total spent, average hourly rate paid, hours paid, hire rate, account creation date, jobs posted, open jobs, hires, active hires, work history, company size and industry |
The client's name is never returned. link is a short flconsole link that opens the job on Upwork; if a short link can't be made, it is the direct upwork.com link.
Limits
| What | Limit |
|---|---|
Jobs via find_jobs | 100 an hour and 1,000 a day, across all feeds, filters and connections |
Full job details (get_job_details) | 30 jobs an hour, up to 5 per call |
| Job age | Posted in the last 30 minutes; no search in older jobs |
| Checks for new jobs | At most once every 60 seconds; every 5–15 minutes is enough for monitoring |
find_jobs with filters or a feed with alerts off | At most 100 matches in the window, otherwise filters_too_broad |
| Feeds with Telegram alerts | 5, shared with the bot; paused feeds count too |
| Feeds for your agent (alerts off) | 5 more, separate from feeds with alerts |
| Feed changes (create, update, alerts, pause, delete) | 20 an hour, for both kinds of feeds |
Changes to the agent's notes (about you and agent_notes of feeds) | 30 an hour |
| Agent's notes about you | 6,000 characters |
AI filter / agent_notes of a feed | 2,000 / 1,500 characters |
preview_filters | 10 an hour |
parse_upwork_url | 30 an hour |
| All tool calls | 60 a minute per connection |
| Connections | 5: sign-ins and manual tokens together |
Hourly quotas reset at the start of each hour (UTC), the daily quota at midnight UTC. get_usage shows what's left. MCP quotas don't affect Telegram alerts, and Telegram alerts don't use MCP quotas.
Errors

A failed call returns a normal tool result marked as an error, so your agent can read it and fix the call:
{ "error": { "code": "filters_too_broad", "message": "…", "field": "filters", "retry_after_seconds": 60 } }field and retry_after_seconds appear when they apply.
| Code | What it means |
|---|---|
invalid_request | An argument is missing or wrong; field names it |
invalid_filters | A filter is unknown or has a wrong value; field is its path, like base.hourly_rate |
invalid_query | Upwork search can't read base.q, or it is too short or too long |
not_found | No such feed among yours |
confirmation_required | A change that needs your approval without user_confirmed: true |
feed_paused | find_jobs by a paused feed; resume it with set_feed_paused or search with filters |
feed_limit_reached | You already have 5 feeds of that kind (alerts on, or alerts off) |
too_early | Checked again sooner than 60 seconds |
quota_exhausted | The hourly or daily find_jobs quota is used up |
rate_limited | Another hourly limit is used up, or more than 60 calls a minute |
filters_too_broad | Filters, or a feed with alerts off, match more than 100 new jobs |
unavailable | Temporary problem on our side; try again later |
filters_too_broad
Your filters (or a feed with alerts off) match more than 100 jobs in the window. Nothing is returned and no quota is used. Put every criterion into filters: category, job type, rate or budget, experience level, location, client statistics. Make the search more specific with OR, AND and parentheses. preview_filters shows how many jobs a set of filters matches. Try again after retry_after_seconds.
Quota exceeded
quota_exhausted means the 100 jobs for this hour or the 1,000 for today have already been returned. The message says when the quota resets; retry_after_seconds is the wait. get_job_details and the other tools answer rate_limited when their hourly limit is used up. Narrow your filters so fewer, better jobs use the quota.
skipped_count
skipped_count above 0 means more jobs matched than were returned. The skipped jobs are not returned later. The response then also has a warning. Narrow the filters or the feed's search so that everything that matches fits into one response.
Too frequent checks
too_early means less than 60 seconds have passed since your last check. Wait retry_after_seconds. Nothing is lost: the next check returns the jobs posted in between. For regular monitoring, a check every 5–15 minutes is enough.
Security
Sign-in through Telegram. You approve each new connection in the bot and enter a 4-digit code on the sign-in page. Never share the code: whoever has it gets access to your feeds.
No password, no API key. Connections use tokens; flconsole stores only their hashes. A sign-in session lasts up to 90 days from its last use.
Every change to your alerts is reported in Telegram. When your agent creates, changes, pauses or resumes a feed with alerts, turns alerts on or off, or deletes any feed, the bot tells you. You see it even after
/stop, so you notice a connection you didn't make.Your approval for every change that matters. Saving a feed, turning alerts on or off, deleting a feed, and changing or pausing a feed with alerts require
user_confirmed: true, which your agent may pass only after you agreed in the conversation. Alerts stay off unless you ask for them. Feeds with alerts off and the agent's notes send nothing to Telegram, so the agent tunes them without asking each time.Disconnect any time. In the bot, send
/mcp: it lists your connections with the date they were created and last used. Disconnect one, and it loses access right away. Your feeds and the agent's notes stay.No access to your Upwork account. flconsole collects Upwork jobs itself. The server reads only those jobs and what you keep in flconsole: feeds and the agent's notes.
See also: Privacy.
Good to know
Can the agent search old jobs?
No. Only jobs posted in the last 30 minutes.
Does my agent get jobs pushed to it?
No. It checks when you ask or on a schedule. Telegram alerts arrive within a minute.
What does the agent see about a job?
Title, description, skills, job type, budget or rate, and the client's country. Full details are available for the jobs it picks.
Where does my agent keep my setup?
With way 2, on flconsole's server: up to 5 feeds with alerts off (with the agent's notes for each) and its notes about you, until you delete them. You see the feeds in the bot's /feeds; delete one there or ask your agent, and ask it to clear its notes. See Privacy.
How do I disconnect an agent?
In the Telegram bot: /mcp.
Connect your agent
Claude Code
claude mcp add --transport http flconsole https://mcp.lite.flconsole.com/mcpThen run /mcp → Authenticate. You'll confirm in Telegram — no password, no token.
Codex
codex mcp add flconsole --url https://mcp.lite.flconsole.com/mcpcodex mcp login flconsole
A browser opens — confirm in Telegram and you're in.
Claude app
Customize → Connectors → + → Add custom connector
https://mcp.lite.flconsole.com/mcpWorks on web, desktop and mobile. You'll confirm in Telegram.
Cursor
{"mcpServers": {"flconsole": {"url": "https://mcp.lite.flconsole.com/mcp"}}}
Add it to ~/.cursor/mcp.json, then sign in when Cursor asks.
Free · Sign in with Telegram · No API key