ponisha-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PONISHA_MCP_PROXY | No | HTTP proxy URL, or a comma-separated list of proxy URLs. System proxy settings are ignored. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| pn_search_projectsA | Search Ponisha projects (Iran's freelance marketplace) by text, skills, category, status and budget. Use this to find work to bid on or to see what employers ask for. Results are compact cards; call pn_project for the full brief and competition, pn_bids for the offers already made. Budget filters are applied to the fetched page (the site has none), so with a budget filter up to 50 projects per page are scanned. |
| pn_projectA | Get one Ponisha project: full description, budget, skills, deadline and the employer's track record. Use after pn_search_projects. The employer block (projects created/completed, rating, member since) shows whether the employer pays and finishes work. A finished project also shows accepted_price (what the winner was paid) and done_by. Set include_bid_sample=true for price statistics of the first 20 offers (slow on projects with many bids: Ponisha takes up to 30 s); pn_bids lists the offers themselves, pn_reviews the employer's reviews, pn_user_projects the employer's other projects. |
| pn_bidsA | List the offers freelancers made on a Ponisha project: price, days, pitch and each bidder's track record. Use to see the competition on a project before bidding or to compare bidders. Prices are Toman. Bidder
names link to pn_profile. Ponisha serves these slowly (about 3 s, up to 30 s on projects with 100+ bids), so
keep limit small; page through with |
| pn_search_freelancersA | Search Ponisha freelancers by text, skills, category, level and portfolio, ranked by score. Use to find who to hire or to see who leads a niche. Cards carry score, average rating and review count; call pn_profile for the full profile, pn_reviews for what employers wrote, pn_portfolios for their work. Rating is the average employer score (max 5). The site has no city filter. |
| pn_profileA | Get a public Ponisha profile (freelancer or employer): level, skills, statistics, rating and activity. Use for a username from pn_search_freelancers, pn_bids or pn_project. Shows completed projects, rating, response rate, member since and last seen; include_resume adds their work history. Next: pn_reviews, pn_portfolios, pn_user_projects. Private data (contact, real name) is not available. |
| pn_skillsA | Find Ponisha skills (about 700 tags) by name to use in the skills filters of other tools. Use first when the user names a skill; pass the returned slug or id as |
| pn_categoriesA | List Ponisha's top-level project categories, or the sub-categories of one. Use to get the |
| pn_marketA | Summarize demand and supply for one skill on Ponisha: open projects, budgets, competition, related skills. Use for "is it worth bidding on X", "what do X projects pay" or "how crowded is X". Based on the 50 newest open projects with that skill (budgets in Toman, medians of the project budget midpoints) and the freelancer count for the skill. |
| pn_reviewsA | Read the reviews employers wrote about a Ponisha user, or recent reviews for a whole skill. Give exactly one of username or skill. For a user it also returns the score summary (star counts, quality, communication, timeline, expertise, hire-again averages, success rate): use it to judge a freelancer before hiring or an employer before bidding. For a skill it shows what employers praise or complain about in that field (only the newest 2000 reviews are reachable). Next: pn_profile, pn_project. |
| pn_portfoliosA | Search Ponisha portfolio items (about 500k work samples), or list one user's portfolio. Use to see real examples of a kind of work or to check what a freelancer has built. Search is ranked by Ponisha's quality score; items carry views, likes, skills and the author. With username, query/skills are ignored and the user's items are listed (title and link only). Next: pn_profile for the author. |
| pn_servicesA | Browse Ponisha's ready-made service packages (fixed-price offers such as logo design or WordPress themes). Use when the user wants to buy a defined service at a known price instead of posting a project. About 80 packages exist in a few categories. Prices are Toman. Next: pn_service for deliverables and add-ons, pn_profile for the seller. |
| pn_serviceA | Get one Ponisha service package: price, delivery time, what is included, requirements and paid add-ons. Use after pn_services to compare what a fixed-price offer really delivers. Prices are Toman. |
| pn_user_projectsA | List the projects a Ponisha user is attached to: an employer's own projects or a freelancer's finished work. Use to check an employer's history (what they ask for, how many finish) or what a freelancer has delivered. Call pn_project with an id for the full brief and the accepted price. |
| pn_trendA | Show how demand and budgets for one skill changed over time on Ponisha, from the newest to the oldest projects. Use for "is demand for X growing" or "what did X pay a year ago". Samples |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 14 tools
Each tool maps to a distinct resource+action pair, and the list/detail pairs (pn_services/pn_service, pn_search_projects/pn_project, pn_search_freelancers/pn_profile) are spelled out in the descriptions. The closest pair, pn_market vs pn_trend, is explicitly split into current snapshot vs historical sampling, and pn_bids is clearly separated from bid statistics inside pn_project. Cross-references ('Next: pn_reviews, pn_portfolios') actively steer the agent to the right follow-up tool.
Every tool carries the same pn_ prefix in snake_case and follows a stable convention: search_<plural> for searches, bare singular noun for single-entity getters, and plural nouns for lists. There is no style drift (no camelCase, no stray verbs), so names are predictable from first glance.
Fourteen tools sit in the well-scoped range and each covers a genuinely different surface (projects, freelancers, profiles, bids, reviews, portfolios, services, skills, categories, market, trend). No obvious filler or redundant tool is present, and the navigation tools (pn_skills, pn_categories) are justified because they feed filter parameters elsewhere.
The surface is broad and coherent for a read-only marketplace research server: discovery, detail, reputation, portfolios, pricing analytics and trend history are all covered with no dead ends. Minor gaps remain, such as no way to search employers directly or to list a single freelancer's bids/submissions, though agents can work around these via pn_user_projects and pn_bids.