@simplysf/simply-atlassian-mcp 0.4.1 → 0.4.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +79 -2
  2. package/package.json +2 -2
package/README.md CHANGED
@@ -3,8 +3,8 @@
3
3
  [![NPM](https://img.shields.io/npm/v/@simplysf/simply-atlassian-mcp?label=@simplysf/simply-atlassian-mcp)](https://npmjs.com/@simplysf/simply-atlassian-mcp) [![License: Apache-2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](https://raw.githubusercontent.com/SimplySF/simply-atlassian/main/LICENSE.txt)
4
4
 
5
5
  A [Model Context Protocol](https://modelcontextprotocol.io/) server that gives an AI agent in
6
- Claude Desktop, Claude Code, Cursor, VS Code, or any other MCP client the same Jira and Confluence
7
- capabilities as the [`@simplysf/simply-atlassian`](../simply-atlassian) CLI: one tool per command,
6
+ Claude Desktop, Claude Code, Cursor, Gemini, VS Code, or any other MCP client the same Jira and
7
+ Confluence capabilities as the [`@simplysf/simply-atlassian`](../simply-atlassian) CLI: one tool per command,
8
8
  calling the same [`@simplysf/simply-atlassian-core`](../simply-atlassian-core) library in-process.
9
9
  The agent gets the CLI's credential handling, `dryRun` previews, read-only guard, credential
10
10
  redaction, and error messages, and the same raw JSON the CLI prints with `--json`, without a
@@ -109,6 +109,83 @@ servers and whether each one connected.
109
109
  Cursor reads `.cursor/mcp.json` in the project, or `~/.cursor/mcp.json` for every project, with
110
110
  the same `mcpServers` shape as Claude Desktop.
111
111
 
112
+ ### Gemini CLI
113
+
114
+ Gemini CLI reads `~/.gemini/settings.json` for every project, or `.gemini/settings.json` inside a
115
+ project, with the same `mcpServers` shape as Claude Desktop:
116
+
117
+ ```json
118
+ {
119
+ "mcpServers": {
120
+ "simply-atlassian": {
121
+ "command": "simply-atlassian-mcp",
122
+ "args": ["--env-file", "/home/me/atlassian.env"]
123
+ }
124
+ }
125
+ }
126
+ ```
127
+
128
+ `gemini mcp add` writes the same entry. `--scope user` puts it in the global file; the default
129
+ `project` scope writes `.gemini/settings.json`, and `-e` sets one variable on the entry:
130
+
131
+ ```sh
132
+ gemini mcp add --scope user \
133
+ -e JIRA_URL=https://your-site.atlassian.net \
134
+ -e JIRA_USERNAME=you@example.com \
135
+ -e JIRA_API_TOKEN=... \
136
+ simply-atlassian simply-atlassian-mcp
137
+ ```
138
+
139
+ Flags meant for the server itself, `--env-file` and `--allow-writes`, are easier to add by editing
140
+ `settings.json`, because `gemini mcp add` reads a leading-dash argument as one of its own options.
141
+
142
+ Values in `env` expand `$NAME` from the environment Gemini started in, which keeps the token out of
143
+ the settings file without an env file:
144
+
145
+ ```json
146
+ {
147
+ "mcpServers": {
148
+ "simply-atlassian": {
149
+ "command": "npx",
150
+ "args": ["-y", "@simplysf/simply-atlassian-mcp"],
151
+ "env": {
152
+ "JIRA_URL": "https://your-site.atlassian.net",
153
+ "JIRA_USERNAME": "you@example.com",
154
+ "JIRA_API_TOKEN": "$JIRA_API_TOKEN"
155
+ }
156
+ }
157
+ }
158
+ }
159
+ ```
160
+
161
+ Two other fields on an entry matter here. `trust: true` bypasses the per-call confirmation for
162
+ every tool on that server, so leave it off on any entry started with `--allow-writes` and let a
163
+ person approve each write. `includeTools` and `excludeTools` narrow what the model is shown, which
164
+ is a second way to express the split in [Let the agent write](#let-the-agent-write): a write entry
165
+ can register the write tools while holding back the destructive ones.
166
+
167
+ ```json
168
+ {
169
+ "mcpServers": {
170
+ "simply-atlassian-write": {
171
+ "command": "simply-atlassian-mcp",
172
+ "args": ["--allow-writes", "--env-file", "/home/me/atlassian-write.env"],
173
+ "excludeTools": ["jira_issue_delete", "jira_issue_comment_delete", "confluence_page_delete"],
174
+ "trust": false
175
+ }
176
+ }
177
+ }
178
+ ```
179
+
180
+ Inside a session, `/mcp` lists the configured servers, whether each connected, and the tools it
181
+ registered.
182
+
183
+ ### Gemini Code Assist
184
+
185
+ Agent mode in the VS Code extension reads that same `~/.gemini/settings.json`, so an entry added
186
+ for Gemini CLI is already in place. In IntelliJ the file is `mcp.json` in the IDE's configuration
187
+ directory, holding the same `mcpServers` object.
188
+
112
189
  ### VS Code
113
190
 
114
191
  VS Code reads `.vscode/mcp.json`, with a `servers` key and an explicit transport type:
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "@simplysf/simply-atlassian-mcp",
3
3
  "description": "Model Context Protocol server exposing Jira and Confluence to AI agents, built on @simplysf/simply-atlassian-core",
4
- "version": "0.4.1",
4
+ "version": "0.4.2",
5
5
  "author": "@ClayChipps",
6
6
  "homepage": "https://github.com/SimplySF/simply-atlassian",
7
7
  "bugs": "https://github.com/SimplySF/simply-atlassian/issues",
@@ -167,5 +167,5 @@
167
167
  "service": true
168
168
  }
169
169
  },
170
- "gitHead": "b0d86a9014b4e6483898577781f4090a20685b70"
170
+ "gitHead": "00dc34e673af42a05947595409e63cad9bd37d62"
171
171
  }