Bridge by Wekoya / Docs / Get started
MCP server
Updated
Bridge has an MCP server, so an AI assistant or coding agent can use Bridge for you: find and price models, run and compare them, make pictures, videos, speech and music, transcribe recordings, estimate what a feature will cost, find the cheapest model that still passes your own examples and put it live, explain what you spent, and set budgets. It works in Claude, ChatGPT, Claude Code, Codex, Cursor, VS Code and any other MCP client, at https://wekoya-api.wekoya.tech/mcp. To see it at work, with real pictures and videos it made, go to bridge.wekoya.tech/mcp.
In Claude or ChatGPT
Add a custom connector with the address above. You are sent to Bridge to sign in and choose what the app may do, the most it may spend a month in naira, and when it stops working. The app gets a key of its own, shown under API keys as "MCP: Claude" (or the app's name); revoke it there to disconnect.
In a coding agent
Use a Bridge key as the bearer token. Claude Code:
claude mcp add --transport http bridge https://wekoya-api.wekoya.tech/mcp \
--header "Authorization: Bearer $WEKOYA_API_KEY"Cursor (~/.cursor/mcp.json), and the same shape for Cline:
{
"mcpServers": {
"bridge": {
"url": "https://wekoya-api.wekoya.tech/mcp",
"headers": { "Authorization": "Bearer ${env:WEKOYA_API_KEY}" }
}
}
}VS Code (.vscode/mcp.json), which asks for the key once and keeps it out of the file:
{
"servers": {
"bridge": {
"type": "http",
"url": "https://wekoya-api.wekoya.tech/mcp",
"headers": { "Authorization": "Bearer ${input:bridge-key}" }
}
},
"inputs": [
{ "type": "promptString", "id": "bridge-key", "description": "Bridge API key", "password": true }
]
}Codex:
# ~/.codex/config.toml
[mcp_servers.bridge]
url = "https://wekoya-api.wekoya.tech/mcp"
bearer_token_env_var = "WEKOYA_API_KEY"Give the agent a key with only what it needs: chat and models to run models, usage to read spending, and a monthly limit. The bridge_agent_key tool makes one.
The tools
| Tool | What it does |
|---|---|
bridge_models_search | Find models by ability, maker, price and context, with naira prices. |
bridge_docs_search | The parts of these docs that answer a question. |
bridge_web_search | Search the live web, with a cited answer. |
bridge_chat | Run a prompt on any model: answer, cost, tokens, time. |
bridge_compare_models | One prompt on 2 to 6 models, side by side; with criteria, a judge scores each and names the best value. Consensus mode is a second opinion. |
bridge_decide | Typed decisions from Jev: a label, a score or yes/no, with probabilities. |
bridge_media_models | The picture, video, voice, transcription and music models: what each takes, its options and its naira price. |
bridge_generate_image | Make pictures, or edit and combine pictures you give it, with GPT Image or Gemini. |
bridge_generate_video | Start a Veo video from a prompt or a first frame, or a talking video from a picture and a voice. |
bridge_media_status | A video's progress and download link; a file's link and how long it is kept. |
bridge_generate_speech | Read text aloud in a chosen voice, or as a two-person dialogue. |
bridge_transcribe | Turn a recording into text. |
bridge_generate_music | A music clip or a full song from a prompt, with lyrics. |
bridge_media_upload | An address to upload a local picture or recording to, for agents that run commands. |
bridge_cost_estimate | What a feature will cost a month on several models, before building it. |
bridge_optimise_plan | Find a cheaper model: save real examples and get a quote. Spends nothing. |
bridge_optimise_run | Run the quoted test once the user approves the cost. |
bridge_optimise_status | The verdict: switch, switch with fallback, keep, or add examples, with the monthly saving. |
bridge_deploy | Put a tested setup live under a stable name (cfg:name), or roll back. |
bridge_spend_explain | What was spent, what changed and why, and what to change, with the naira saving. |
bridge_budget | Balance, burn rate, days left, this key's limit, users near their budget. |
bridge_agent_key | A key with a monthly naira cap and an expiry, for an agent or a teammate. |
bridge_end_users | Your users' spend and budgets; set one user's budget. |
bridge_design_solution | Turn a problem into a design: steps, models, cost per request and month, risks. |
bridge_integrate | The exact changes to move OpenAI, Anthropic or Gemini code onto Bridge. |
Pictures, video, voice and music
- Ask for the price first: each media tool takes
quote_onlyand answers what it would cost without making anything. A video is never started withoutmax_cost_ngn, so the assistant has to tell you the price and get your go-ahead. - Everything made gets a media id and a download link, kept for 48 hours. The assistant passes the media id to the next step instead of the file: a picture becomes a video's first frame or the subject of an edit, speech becomes the voice of a talking video, a recording is transcribed.
- Videos take one to five minutes.
bridge_generate_videoanswers at once with an id, andbridge_media_statuswaits for the link. A video that fails costs nothing. - To work from your own files, give an https link, or (in a coding agent) let it upload the file with
bridge_media_upload. Uploads are kept 48 hours and used only as inputs.
Spending stays in your hands
- Every tool acts as the key it was given: its scopes, its model list and its spending limit apply.
- Tools that spend say what it cost, and refuse before sending anything when the most it could cost is above
max_cost_ngn. - Finding a cheaper model is quoted first and spends nothing until you approve; if the price moves above what you approved, it asks again.
- Putting a setup live, making a key and changing a user's budget need an explicit confirmation.
- Answers from models and web pages come back marked as content, never as instructions.
Prompts and resources
Clients that show MCP prompts get ready-made workflows: switch a feature to a cheaper model, explain my bill, add an AI feature, compare models on my prompt, and estimate a feature's cost. Resources include the model list with naira prices and every docs page as Markdown (bridge://docs/<topic>).