Stack Exchange connector for AI agents

Tools your developer agent reaches for on Stack Exchange, scoped per user.

CALL ANY TOOL

113 tools for developer Q&A on Stack Exchange: search and read questions, answers, comments, and tags, post and edit questions and answers, vote and bookmark, and read the user's inbox, reputation, and badges.

stackexchange_answer_accept

Answer accept

Mark an answer as accepted on a question the signed-in user asked. Returns the accepted answer. Use this only on answers to the user's own questions, when no other answer is accepted. Use stackexchange_answer_accept_undo to remove the accept. Requires the write_access scope.

Parameters

Name

Type

Required

Description

answer_id

integer

Required

ID of the answer.

site

string

Required

Stack Exchange site to use, as its api_site_parameter (for example stackoverflow, superuser, serverfault, askubuntu, math) or full domain (stackoverflow.com). Get the values from stackexchange_sites_list.

preview

boolean

Optional

true to validate the request and return the would-be result without saving anything (default false).

stackexchange_answer_comments_list

List answer comments

stackexchange_answer_create

Create answer

stackexchange_answer_delete

Delete answer

stackexchange_answer_downvote_undo

Answer downvote undo

stackexchange_answer_edit

Answer edit

stackexchange_answers_get

Get answers

stackexchange_badge_recipients_list

List badge recipients

stackexchange_collective_tags_list

List collective tags

stackexchange_comment_upvote_undo

Comment upvote undo

stackexchange_filters_get

Get filters

stackexchange_inbox_list

List inbox

stackexchange_me_badges_list

List me badges

stackexchange_me_privileges_list

List me privileges

stackexchange_me_tags_list

List me tags

stackexchange_notifications_unread_list

List notifications unread

stackexchange_posts_list

List posts

stackexchange_question_downvote_undo

Question downvote undo

stackexchange_question_linked_list

List question linked

List questions that link to one or more questions (including duplicates pointing at them). Returns question_id, title, tags, score and link for each linking question. Use stackexchange_question_linked_list for explicit links. Use stackexchange_question_related_list for similar questions with no link.

Parameters

Name

Type

Required

Description

question_ids

string

Required

Semicolon-separated question IDs, up to 100, e.g. 11227809;927358.

site

string

Required

filter

string

Optional

Response filter: a built-in name (default, withbody to add body fields, none, total for just the count) or a custom filter id from stackexchange_filter_create. Leave empty for the default filter.

fromdate

integer

Optional

Only include items dated on or after this time, as Unix epoch seconds, e.g. 1704067200 for 2024-01-01.

max

string

Optional

Upper bound for the chosen sort field, inclusive: Unix epoch seconds or a number depending on the sort (see sort). Ignored by sorts without min/max.

min

string

Optional

Lower bound for the chosen sort field, inclusive: Unix epoch seconds or a number depending on the sort (see sort). Ignored by sorts without min/max.

order

string

Optional

Sort direction: desc (default) or asc. One of: `desc`, `asc`.

page

integer

Optional

Page of results to return, starting at 1 (default 1). The response's has_more tells you whether another page exists.

pagesize

integer

Optional

Number of items per page, 0 to 100 (default 30).

sort

string

Optional

Field to sort by (default activity): activity (last activity date; min/max are Unix epoch seconds), votes (score; min/max are a number), creation (creation date; min/max are Unix epoch seconds), rank (badge rank; no min/max). One of: `activity`, `votes`, `creation`, `rank`.

todate

integer

Optional

Only include items dated on or before this time, as Unix epoch seconds, e.g. 1735689599 for 2024-12-31.

stackexchange_question_timeline_get

Get question timeline

stackexchange_questions_no_answers_list

List questions no answers

stackexchange_questions_search

Search questions

Search a site's questions by words in the title and/or by tags. Returns question_id, title, tags, score, answer_count and link. Use stackexchange_questions_search for a quick title or tag lookup; at least one of intitle or tagged is required. Use stackexchange_questions_search_advanced for full-text search with more filters, or stackexchange_search_excerpts for result snippets.

Parameters

Name

Type

Required

Description

site

string

Required

filter

string

Optional

Response filter: a built-in name (default, withbody to add body fields, none, total for just the count) or a custom filter id from stackexchange_filter_create. Leave empty for the default filter.

fromdate

integer

Optional

Only include items dated on or after this time, as Unix epoch seconds, e.g. 1704067200 for 2024-01-01.

intitle

string

Optional

Text that must appear in the question title. Required unless tagged is set.

max

string

Optional

Upper bound for the chosen sort field, inclusive: Unix epoch seconds or a number depending on the sort (see sort). Ignored by sorts without min/max.

min

string

Optional

Lower bound for the chosen sort field, inclusive: Unix epoch seconds or a number depending on the sort (see sort). Ignored by sorts without min/max.

nottagged

string

Optional

Semicolon-separated tags that no result may carry, e.g. java;php. Only used when tagged is also set.

order

string

Optional

Sort direction: desc (default) or asc. One of: `desc`, `asc`.

page

integer

Optional

Page of results to return, starting at 1 (default 1). The response's has_more tells you whether another page exists.

pagesize

integer

Optional

Number of items per page, 0 to 100 (default 30).

sort

string

Optional

Field to sort by (default activity): activity (last activity date; min/max are Unix epoch seconds), votes (score; min/max are a number), creation (creation date; min/max are Unix epoch seconds), relevance (search relevance; no min/max). One of: `activity`, `votes`, `creation`, `relevance`.

tagged

string

Optional

Semicolon-separated tags; each result has at least one of them, e.g. python;pandas.

todate

integer

Optional

Only include items dated on or before this time, as Unix epoch seconds, e.g. 1735689599 for 2024-12-31.

stackexchange_tag_faq_list

List tag faq

stackexchange_tag_synonyms_get

Get tag synonyms

stackexchange_tag_top_askers_list

List tag top askers

stackexchange_user_associated_list

List user associated

stackexchange_user_mentions_list

List user mentions

stackexchange_user_questions_list

List user questions

stackexchange_user_reputation_list

List user reputation

stackexchange_user_top_tags_list

List user top tags

For more tools, view docs.

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Stack Exchange tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stackexchange"], toolNames: [
    "stackexchange_questions_search_advanced",
    "stackexchange_question_answers_list",
    "stackexchange_answer_create"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Find accepted answers on Stack Overflow about Postgres advisory locks" }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stackexchange"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Find accepted answers on Stack Overflow about Postgres advisory locks" }],
  tools,
});

// Execute the tool call with the user's vaulted Stack Exchange OAuth token
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stackexchange"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Find accepted answers on Stack Overflow about Postgres advisory locks" }],
  tools,
});

// Tool call runs with the user's vaulted Stack Exchange OAuth token
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["stackexchange"] }, pageSize: 100,
});

const agent = new Agent({
  name: "developer_agent",
  model: "gemini-2.5-pro",
  instruction: "Stack Exchange tools scoped to this user",
  tools,
});

await agent.run("Find accepted answers on Stack Overflow about Postgres advisory locks");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Stack Exchange tool. Click to copy, paste into your agent, done.

Search and read

Copy the prompt

Copied

Search Stack Overflow for accepted answers about Postgres advisory locks.

Copy the prompt

Copied

Find questions similar to: How do I retry a failed Celery task?

Copy the prompt

Copied

List the FAQ questions in the rust tag.

Post and engage

Copy the prompt

Copied

Post an answer to question 78451230 with this code sample.

Copy the prompt

Copied

Upvote the accepted answer on question 11227809.

Copy the prompt

Copied

Bookmark question 4842424 for later.

My account

Copy the prompt

Copied

Show my unread inbox items across all sites.

Copy the prompt

Copied

What are my top tags on Stack Overflow?

Copy the prompt

Copied

List unanswered questions in my favorite tags.

SEE HOW AUTH WORKS

Each user signs in to Stack Exchange once, and Scalekit stores and refreshes their tokens. Credentials stay vaulted, every call is scope checked, and every action is logged.

Authorize

Your user connects

Stack Exchange

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Stack Exchange

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Stack Exchange

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Stack Exchange

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other developer tools and knowledge connectors.

Engineering Teams

Engineering standup agent

Pulls commits from GitHub and GitLab, tracks issue movement in Jira, and posts a per-engineer standup brief to Slack. Each engineer's activity is read on their own delegated OAuth.

Engineering Teams

Slack triage

Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Stack Exchange token looks fine in a demo. In production every answer and vote looks like one service account, and you cannot tell which user triggered it. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Stack Exchange today. Ten connectors tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Stack Exchange as the user or through a shared service account?

As the user. Each user signs in to Stack Exchange once, and Scalekit stores and refreshes their tokens. Questions, answers, comments, and votes the agent posts appear under that user's account and in your audit trail, not a shared service account.

Where is the Stack Exchange OAuth token stored?

In Scalekit's managed AES-256 token vault, namespaced per tenant. Refresh is automatic. Revocation is a single dashboard action. Credentials never appear in prompts, logs, or LLM context.

Can I limit what the agent does in Stack Exchange?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example search and read tools without stackexchange_answer_create and stackexchange_question_delete, so the agent can research but never post or delete. Scalekit also enforces scope checks before every API call.

What happens when a user revokes Stack Exchange access?

The connection is invalidated on the next tool call. Subsequent requests for that user fail closed with a clear error. Other users in the tenant remain unaffected. The event is logged for audit.

Which Stack Exchange sites can the agent use?

Any site in the network. stackexchange_sites_list returns every site, including Stack Overflow, Super User, Server Fault, and Ask Ubuntu, and most tools take the site as a parameter. Inbox and notification tools read across all sites at once.